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. 123641
    Prev
    Next
    INDEX
    Explanations

    Comparisons

    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
     returning
    -0.07
    _isr
    -0.06
     oldValue
    -0.06
     remarkably
    -0.06
    leyici
    -0.06
     sparing
    -0.06
     бути
    -0.06
    里
    -0.06
     Goldberg
    -0.06
    bite
    -0.06
    POSITIVE LOGITS
     ↔
    0.08
     talent
    0.06
     Goku
    0.06
    Entr
    0.06
    (_,
    0.06
    getContext
    0.06
    쇼
    0.06
     peně
    0.06
     广
    0.06
    *',
    0.06
    Activations Density 0.083%

    No Known Activations