© 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 EvalsExportsAPI 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. 23-RESID-POST-AA
    11. 64633
    Prev
    Next
    INDEX
    Explanations

    Ver

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     �
    -0.07
    酸
    -0.06
     luxe
    -0.06
    株
    -0.06
    uml
    -0.06
     Gibbs
    -0.06
     순
    -0.06
     softmax
    -0.06
    灯
    -0.06
    âr
    -0.06
    POSITIVE LOGITS
     ver
    0.08
     Ver
    0.07
    Ver
    0.06
    verb
    0.06
    .EditText
    0.06
     ник
    0.06
    .SUCCESS
    0.06
    VER
    0.06
    oleans
    0.06
     Yok
    0.06
    Activations Density 0.011%

    No Known Activations