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. 15-RESID-POST-AA
    6. 31224
    Prev
    Next
    INDEX
    Explanations

    do

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .requestFocus
    -0.07
    ,’’
    -0.07
     BigNumber
    -0.07
    descending
    -0.06
     cared
    -0.06
     Snapchat
    -0.06
     Indians
    -0.06
    .Vertical
    -0.06
     foregoing
    -0.06
    _units
    -0.06
    POSITIVE LOGITS
     yayım
    0.07
    UpDown
    0.07
     reimburse
    0.07
     inc
    0.06
    (idx
    0.06
     estava
    0.06
     Atom
    0.06
    Win
    0.06
    alarını
    0.06
    ----↵
    0.06
    Activations Density 0.000%

    No Known Activations