Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 104020
    Prev
    Next
    INDEX
    Explanations

    error messages and requests

    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
    XE
    -0.07
    *z
    -0.07
    <(
    -0.07
     patt
    -0.06
     wil
    -0.06
     We
    -0.06
     lệ
    -0.06
     zu
    -0.06
    ées
    -0.06
    We
    -0.06
    POSITIVE LOGITS
    _req
    0.07
    /close
    0.07
     Experience
    0.07
    .Address
    0.07
     ARGS
    0.06
     unmarried
    0.06
    .squareup
    0.06
    .request
    0.06
    :href
    0.06
    IsUnicode
    0.06
    Activations Density 0.004%

    No Known Activations