© 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. 99354
    Prev
    Next
    INDEX
    Explanations

    traffic

    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
     notamment
    -0.07
     tzv
    -0.07
     reachable
    -0.06
     diversos
    -0.06
     jä
    -0.06
    ­tion
    -0.06
    hot
    -0.06
    頓
    -0.06
     бла
    -0.06
     glue
    -0.06
    POSITIVE LOGITS
     hoped
    0.07
    (PHP
    0.06
    _SELECTED
    0.06
     Needs
    0.06
    。」↵↵
    0.06
    Com
    0.06
    navigationBar
    0.06
    链接
    0.06
    .NewRequest
    0.06
     шаг
    0.06
    Activations Density 0.013%

    No Known Activations