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. 27-RESID-POST-AA
    6. 109656
    Prev
    Next
    INDEX
    Explanations

    as

    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
     racer
    -0.06
     Ignore
    -0.06
     obras
    -0.06
    ax
    -0.06
     bride
    -0.06
    ActivityCreated
    -0.06
    ubah
    -0.06
     zprávy
    -0.06
    arefa
    -0.06
     rhyme
    -0.06
    POSITIVE LOGITS
    ,一
    0.08
    ::|
    0.07
     一
    0.06
    突然
    0.06
     ¥
    0.06
     BIN
    0.06
    .optim
    0.06
     ΕΛ
    0.06
     veg
    0.06
     HomeComponent
    0.06
    Activations Density 0.031%

    No Known Activations