© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 57207
    Prev
    Next
    INDEX
    Explanations

    Text processing/NLP

    np_max-act · gemini-2.0-flash

    terms related to statistical concepts like incidence and prevalence.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron fires on the part of the entity‐definition instructions that tells the system to extract the incidence_prevalence entity “when the input explicitly mentions the terms ‘incidence’, ‘prevalence’, or ‘prevalent.’”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     userList
    -0.07
     Giuliani
    -0.07
    -Allow
    -0.07
     Clubs
    -0.07
    ective
    -0.07
    (LogLevel
    -0.06
    anguage
    -0.06
    Du
    -0.06
    roring
    -0.06
    _CONV
    -0.06
    POSITIVE LOGITS
     الله
    0.07
     decode
    0.06
     thrive
    0.06
     closure
    0.06
    革命
    0.06
    (coord
    0.06
     Cape
    0.06
    setPosition
    0.06
    _MIN
    0.06
    명의
    0.06
    Activations Density 0.046%

    No Known Activations