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. 7-RESID-POST-AA
    6. 85437
    Prev
    Next
    INDEX
    Explanations

    up

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     salle
    -0.07
     enfer
    -0.06
    CID
    -0.06
    OV
    -0.06
     partido
    -0.06
    ότητα
    -0.06
    _retry
    -0.06
     robin
    -0.06
    aman
    -0.06
    Dice
    -0.06
    POSITIVE LOGITS
     up
    0.08
    .flag
    0.07
    XML
    0.07
    xFB
    0.07
     ومع
    0.07
    Line
    0.06
     encounters
    0.06
    -paying
    0.06
    ,buf
    0.06
     빈
    0.06
    Activations Density 0.007%

    No Known Activations