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. 7-RESID-POST-AA
    6. 128980
    Prev
    Next
    INDEX
    Explanations

    /gpl

    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
     isset
    -0.08
    Volt
    -0.07
    事務
    -0.07
    .assets
    -0.07
    ды
    -0.07
    .cont
    -0.06
     віднос
    -0.06
    čan
    -0.06
    Dic
    -0.06
     Cav
    -0.06
    POSITIVE LOGITS
    /lgpl
    0.11
    /gpl
    0.11
    .SendMessage
    0.07
    _FC
    0.06
     background
    0.06
    CLI
    0.06
    DK
    0.06
     suggesting
    0.06
    ITIONAL
    0.06
    343
    0.06
    Activations Density 0.000%

    No Known Activations