© 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. 36936
    Prev
    Next
    INDEX
    Explanations

    Tracks or prints

    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
    leasing
    -0.07
    @↵↵
    -0.07
     WATCH
    -0.06
    doors
    -0.06
    YNC
    -0.06
    _exe
    -0.06
    瓶
    -0.06
    _ne
    -0.06
    berapa
    -0.06
    _ALL
    -0.06
    POSITIVE LOGITS
     tö
    0.08
     MCP
    0.06
     cps
    0.06
     proprio
    0.06
    .left
    0.06
     Reggie
    0.06
     imaginary
    0.06
     morale
    0.06
     remarkably
    0.06
     marked
    0.06
    Activations Density 0.123%

    No Known Activations