© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 63772
    Prev
    Next
    INDEX
    Explanations

    Code

    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
     Steve
    -0.06
    Former
    -0.06
     Yard
    -0.06
     closes
    -0.06
    (Command
    -0.06
    (QString
    -0.06
    gaard
    -0.06
     Evelyn
    -0.06
    have
    -0.06
     Deletes
    -0.06
    POSITIVE LOGITS
    났다
    0.07
    рат
    0.07
    dings
    0.07
    _keywords
    0.06
    _tab
    0.06
    .blob
    0.06
    山市
    0.06
    _hook
    0.06
     nä
    0.06
    月
    0.06
    Activations Density 0.002%

    No Known Activations