© 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. 27-RESID-POST-AA
    11. 46047
    Prev
    Next
    INDEX
    Explanations

    say "Judge"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     writes
    -0.07
     Overrides
    -0.06
    ukarı
    -0.06
     dinheiro
    -0.06
    첨부
    -0.06
    您
    -0.06
    _INFINITY
    -0.06
    Exc
    -0.06
    Interop
    -0.06
    	sound
    -0.06
    POSITIVE LOGITS
    -l
    0.07
    tb
    0.06
    (NS
    0.06
    .mContext
    0.06
    říz
    0.06
     shapes
    0.06
     الأم
    0.06
    fst
    0.06
    ings
    0.06
    ,application
    0.06
    Activations Density 0.046%

    No Known Activations