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. 100934
    Prev
    Next
    INDEX
    Explanations

    He

    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
    _EXPRESSION
    -0.07
    ině
    -0.06
     external
    -0.06
     Sprite
    -0.06
    -Out
    -0.06
    samp
    -0.06
     defenders
    -0.06
     Çağ
    -0.06
     Compensation
    -0.06
     durumunda
    -0.06
    POSITIVE LOGITS
     مج
    0.07
    شناسی
    0.06
    _where
    0.06
    labs
    0.06
    shima
    0.06
    แสง
    0.06
    lesc
    0.06
    .food
    0.06
     bü
    0.06
     culpa
    0.06
    Activations Density 0.103%

    No Known Activations