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. 104186
    Prev
    Next
    INDEX
    Explanations

    public

    np_max-act · gemini-2.0-flash

    Java code declarations that use access modifiers (e.g., method, constructor, or field signatures in declaration lines).

    oai_token-act-pair · gpt-5Triggered by @tcai
    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
     posix
    -0.07
     Sinatra
    -0.07
     principle
    -0.07
    уры
    -0.07
     Prosper
    -0.07
    intendo
    -0.06
    heim
    -0.06
     Filters
    -0.06
     wxT
    -0.06
    فاق
    -0.06
    POSITIVE LOGITS
     jacket
    0.06
     guesses
    0.06
    .solution
    0.06
     بیرون
    0.06
     кл
    0.06
     boo
    0.05
     sát
    0.05
     nghĩ
    0.05
     cầu
    0.05
     assignable
    0.05
    Activations Density 0.011%

    No Known Activations