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. 3-RESID-POST-AA
    6. 94921
    Prev
    Next
    INDEX
    Explanations

    osphate

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )n
    -0.06
     reklam
    -0.06
     cider
    -0.06
     môi
    -0.06
    _R
    -0.06
    *)_
    -0.06
    MarshalAs
    -0.06
     Oscars
    -0.06
    _mD
    -0.06
    )r
    -0.06
    POSITIVE LOGITS
    osphate
    0.14
     helpless
    0.08
     Face
    0.08
     Cortex
    0.07
    Face
    0.07
    (DbContext
    0.07
    .fp
    0.07
     Geographic
    0.07
    /fonts
    0.06
    spark
    0.06
    Activations Density 0.003%

    No Known Activations