© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 91033
    Prev
    Next
    INDEX
    Explanations

    indigenous

    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
    _SQL
    -0.07
     Highlights
    -0.06
     candies
    -0.06
    CreateTime
    -0.06
     PLA
    -0.06
    atron
    -0.06
     balloon
    -0.06
    _jet
    -0.06
    -license
    -0.06
    _CONFIGURATION
    -0.06
    POSITIVE LOGITS
     indigenous
    0.13
     Indigenous
    0.13
    igenous
    0.11
     goddess
    0.07
    ikh
    0.07
    ']));
    0.07
    提供
    0.07
    itness
    0.07
    gh
    0.06
     Hicks
    0.06
    Activations Density 0.002%

    No Known Activations