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. 11-RESID-POST-AA
    6. 80644
    Prev
    Next
    INDEX
    Explanations

    character display problems

    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
    	M
    -0.06
    Computer
    -0.06
    드
    -0.06
     meat
    -0.06
     fr
    -0.06
    ิต
    -0.06
     lipid
    -0.06
    ampus
    -0.06
     Tooth
    -0.06
    ilm
    -0.06
    POSITIVE LOGITS
     연결
    0.07
     그렇게
    0.07
     baskı
    0.06
    _thresh
    0.06
     Zy
    0.06
    只是
    0.06
    ...
    ↵
    0.06
    .gsub
    0.06
     presume
    0.06
    .Enable
    0.06
    Activations Density 0.064%

    No Known Activations