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. 93608
    Prev
    Next
    INDEX
    Explanations

    Software and websites

    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
     Republican
    -0.07
     deep
    -0.07
     小
    -0.07
    #@
    -0.07
     اختصاص
    -0.06
    (Global
    -0.06
     ар
    -0.06
    _game
    -0.06
     Джон
    -0.06
     NL
    -0.06
    POSITIVE LOGITS
     düzenli
    0.06
    MediaPlayer
    0.06
    üş
    0.06
    radan
    0.06
     Rain
    0.06
    �m
    0.06
     mül
    0.06
     Unt
    0.06
     herhangi
    0.06
    getParent
    0.06
    Activations Density 0.231%

    No Known Activations