© 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
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 8950
    Prev
    Next
    INDEX
    Explanations

    history overviews, summaries

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     paris
    -0.07
    ethereum
    -0.07
    ASON
    -0.06
     College
    -0.06
     consent
    -0.06
    英語
    -0.06
    ляється
    -0.06
     ΔΗΜ
    -0.06
    Locale
    -0.06
    }$
    -0.06
    POSITIVE LOGITS
    omen
    0.07
    los
    0.07
     την
    0.06
    ských
    0.06
     fortified
    0.06
     improvements
    0.06
    сп
    0.06
    днання
    0.06
     harassing
    0.06
    _theme
    0.06
    Activations Density 0.053%

    No Known Activations