© 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. 116055
    Prev
    Next
    INDEX
    Explanations

    Different approaches/variations

    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
    訓
    -0.06
    희
    -0.06
     bland
    -0.06
    plot
    -0.06
     authoritarian
    -0.06
    small
    -0.06
    Fil
    -0.06
    +C
    -0.06
     hostages
    -0.06
     quelque
    -0.06
    POSITIVE LOGITS
     SUBSTITUTE
    0.06
    Live
    0.06
     poisoned
    0.06
     PSA
    0.06
     utf
    0.06
    .ToolTip
    0.06
     approved
    0.06
     Hund
    0.06
    .ERR
    0.06
     License
    0.06
    Activations Density 0.152%

    No Known Activations