© 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. 7-RESID-POST-AA
    11. 93799
    Prev
    Next
    INDEX
    Explanations

    chronological order

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .shop
    -0.06
    mrt
    -0.06
    _byte
    -0.06
    也有
    -0.06
     standing
    -0.06
     英语
    -0.06
    Piece
    -0.06
     counties
    -0.06
    REM
    -0.06
    -standing
    -0.06
    POSITIVE LOGITS
     corruption
    0.06
     multiline
    0.06
    ��
    0.06
    rightarrow
    0.06
     الك
    0.06
    ��
    0.06
     serene
    0.06
    -get
    0.06
    _MATCH
    0.06
    eselect
    0.06
    Activations Density 0.186%

    No Known Activations