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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 18263
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ascending
    -0.07
    .schedule
    -0.07
     天
    -0.06
     premiere
    -0.06
     eoqkrvldkf
    -0.06
     natives
    -0.06
     Milano
    -0.06
    。(
    -0.06
     Pattern
    -0.06
     gaming
    -0.06
    POSITIVE LOGITS
    ournal
    0.07
    ecz
    0.06
    _stmt
    0.06
    iliği
    0.06
    ationally
    0.06
     paypal
    0.06
     χρόνια
    0.06
    897
    0.06
    uito
    0.06
     математи
    0.06
    Activations Density 0.146%

    No Known Activations