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. 123378
    Prev
    Next
    INDEX
    Explanations

    technical jargon

    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
     administering
    -0.06
    -beta
    -0.06
     swollen
    -0.06
    τις
    -0.06
    ArrayOf
    -0.06
    .ind
    -0.06
     unimagin
    -0.06
     @[
    -0.06
     kâ
    -0.06
    ofire
    -0.06
    POSITIVE LOGITS
    념
    0.07
     ContentType
    0.07
     Tigers
    0.07
    udad
    0.06
    	BYTE
    0.06
    _TOPIC
    0.06
     مک
    0.06
     consistently
    0.06
     دقیق
    0.06
     مذ
    0.06
    Activations Density 0.000%

    No Known Activations