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. 21745
    Prev
    Next
    INDEX
    Explanations

    Wikipedia categories

    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
     intest
    -0.06
     Sentry
    -0.06
     score
    -0.06
     Abdel
    -0.06
    SC
    -0.06
     prostoru
    -0.06
    -Semitic
    -0.06
    .IsValid
    -0.06
    /close
    -0.06
     世界
    -0.05
    POSITIVE LOGITS
     Пів
    0.07
    Implementation
    0.07
    issuer
    0.07
    .reply
    0.07
     bom
    0.06
     geek
    0.06
     Riot
    0.06
     gtk
    0.06
    (dim
    0.06
    HorizontalAlignment
    0.06
    Activations Density 0.019%

    No Known Activations