© 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. 19-RESID-POST-AA
    11. 109157
    Prev
    Next
    INDEX
    Explanations

    to

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pros
    -0.07
    _pred
    -0.07
     addObject
    -0.06
    -positive
    -0.06
     questionable
    -0.06
    终于
    -0.06
    _nom
    -0.06
     Sup
    -0.06
    ्यप
    -0.06
    structions
    -0.06
    POSITIVE LOGITS
     Ire
    0.06
    (seq
    0.06
     viewers
    0.06
     zk
    0.06
    sdk
    0.06
     took
    0.06
    -account
    0.06
     dispatched
    0.06
    begin
    0.06
    new
    0.06
    Activations Density 0.035%

    No Known Activations