© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92112
    Prev
    Next
    INDEX
    Explanations

    study

    np_max-act · gemini-2.0-flash

    The neuron activates on terms marking research design and sample descriptions—words like “study,” “cohort,” “population,” “group,” and “period.”

    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
     retrieve
    -0.07
    fh
    -0.06
    .inline
    -0.06
    creen
    -0.06
    连
    -0.06
     screen
    -0.06
    _use
    -0.06
     Alcohol
    -0.06
    ("[%
    -0.06
     Uh
    -0.06
    POSITIVE LOGITS
    creativecommons
    0.07
    maids
    0.07
    bast
    0.07
    исс
    0.07
     Lafayette
    0.07
    δοση
    0.06
    validator
    0.06
     mücadele
    0.06
     Telerik
    0.06
     proyecto
    0.06
    Activations Density 0.016%

    No Known Activations