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. 53541
    Prev
    Next
    INDEX
    Explanations

    encouragement and guidance

    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
    е�
    -0.08
    ::::::::
    -0.07
     музы
    -0.07
     نگهد
    -0.07
    $max
    -0.07
    luet
    -0.07
     manuals
    -0.07
    爵
    -0.06
    曜
    -0.06
     predatory
    -0.06
    POSITIVE LOGITS
     tí
    0.06
    .getCount
    0.06
     GetUser
    0.06
    .Lines
    0.06
    остью
    0.06
    distinct
    0.06
    涉
    0.06
     Cors
    0.06
    -------↵↵
    0.06
     порядку
    0.06
    Activations Density 0.061%

    No Known Activations