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. 11-RESID-POST-AA
    6. 53176
    Prev
    Next
    INDEX
    Explanations

    patents and inventions

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fab
    -0.07
     میکن
    -0.07
     XM
    -0.06
     MH
    -0.06
    -league
    -0.06
     Incre
    -0.06
        	↵
    -0.06
     human
    -0.06
    ↵↵↵↵↵↵↵
    -0.06
     RSS
    -0.06
    POSITIVE LOGITS
     unidentified
    0.07
    .Status
    0.06
     yorum
    0.06
     itself
    0.06
    Partial
    0.06
     ب
    0.06
    _proto
    0.06
    RelativeTo
    0.06
     Й
    0.06
    には
    0.06
    Activations Density 0.103%

    No Known Activations