© 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 EvalsExportsinterp-engineNEWAPI 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. 58902
    Prev
    Next
    INDEX
    Explanations

    code questions

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of specific software libraries, frameworks, or project names.

    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
    _win
    -0.07
    .slider
    -0.07
     Instagram
    -0.06
    Knife
    -0.06
     &'
    -0.06
    .ReadAllText
    -0.06
     FlatButton
    -0.06
     ณ
    -0.06
    userInfo
    -0.06
    (TABLE
    -0.06
    POSITIVE LOGITS
    、大
    0.07
    lias
    0.07
    elve
    0.07
    дя
    0.06
    oldur
    0.06
     indexed
    0.06
    filt
    0.06
     salv
    0.06
    missing
    0.06
    Mind
    0.06
    Activations Density 0.090%

    No Known Activations