© 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. 49732
    Prev
    Next
    INDEX
    Explanations

    formation

    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
    半
    -0.08
    Time
    -0.07
    markets
    -0.07
     BUF
    -0.06
     rad
    -0.06
     scaled
    -0.06
     usleep
    -0.06
    ディア
    -0.06
     Speech
    -0.06
    ích
    -0.06
    POSITIVE LOGITS
     BÖL
    0.07
    .register
    0.07
    ...↵↵↵↵↵↵
    0.07
    	Result
    0.07
     INSERT
    0.06
    [Index
    0.06
    addEventListener
    0.06
    .DataGridViewContentAlignment
    0.06
    Tesla
    0.06
    เทพ
    0.06
    Activations Density 0.093%

    No Known Activations