Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15-RESID-POST-AA
    6. 123213
    Prev
    Next
    INDEX
    Explanations

    code/random text

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kvinne
    -0.07
    .weight
    -0.07
    ระบบ
    -0.06
    万
    -0.06
    	vertices
    -0.06
    routes
    -0.06
     nearest
    -0.06
    _CC
    -0.06
    �
    -0.06
    sup
    -0.06
    POSITIVE LOGITS
    EntityType
    0.06
    nex
    0.06
    áf
    0.06
    OUCH
    0.06
    iquer
    0.06
    piler
    0.06
    رفته
    0.06
    lectric
    0.06
    тура
    0.06
     exter
    0.06
    Activations Density 0.000%

    No Known Activations