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. 128954
    Prev
    Next
    INDEX
    Explanations

    straight

    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
     psychologists
    -0.07
    хо
    -0.06
     Gow
    -0.06
     Parenthood
    -0.06
    (ids
    -0.06
     Paren
    -0.06
     Nex
    -0.06
    uhan
    -0.06
    subseteq
    -0.05
     Ram
    -0.05
    POSITIVE LOGITS
     itemBuilder
    0.07
    688
    0.07
     فار
    0.07
     ])↵↵
    0.06
     BaseController
    0.06
    730
    0.06
     isten
    0.06
    ان
    0.06
    _VOICE
    0.06
     проведення
    0.06
    Activations Density 0.196%

    No Known Activations