© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 97604
    Prev
    Next
    INDEX
    Explanations

    specific

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     будуть
    -0.06
     будет
    -0.06
     '-';↵
    -0.06
    테
    -0.06
    _test
    -0.06
    _RATE
    -0.06
     był
    -0.06
    advanced
    -0.06
    Formatter
    -0.06
    movement
    -0.06
    POSITIVE LOGITS
     specific
    0.10
     Specific
    0.08
     specificity
    0.07
    )').
    0.07
     PF
    0.07
     SP
    0.07
     BTC
    0.07
     WordPress
    0.07
     specifics
    0.07
     protein
    0.07
    Activations Density 0.007%

    No Known Activations