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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 41625
    Prev
    Next
    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash

    This neuron detects numeric literals (digits and numbers, including decimals) in the text.

    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
     پار
    -0.09
    _Blue
    -0.07
    -Men
    -0.06
    (val
    -0.06
    370
    -0.06
     содерж
    -0.06
    rozen
    -0.06
    OOT
    -0.06
    Ten
    -0.06
    \Bridge
    -0.06
    POSITIVE LOGITS
    ลง
    0.06
     warped
    0.06
     hope
    0.06
    seat
    0.06
    \Repositories
    0.06
    iration
    0.06
    /kubernetes
    0.06
    Correct
    0.06
    observations
    0.06
     Celebrity
    0.06
    Activations Density 0.010%

    No Known Activations