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. 11-RESID-POST-AA
    6. 73261
    Prev
    Next
    INDEX
    Explanations

    of

    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
    、や
    -0.07
     لغ
    -0.06
     BJP
    -0.06
    aurus
    -0.06
     ב
    -0.06
     tsunami
    -0.06
    ESİ
    -0.06
    ylan
    -0.06
    ju
    -0.06
     tín
    -0.06
    POSITIVE LOGITS
     شود
    0.07
    (period
    0.06
    rose
    0.06
     Oriental
    0.06
    [self
    0.06
    ortic
    0.06
     Colon
    0.06
     signature
    0.06
     xhr
    0.06
    :black
    0.06
    Activations Density 0.002%

    No Known Activations