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. 80742
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     IEEE
    -0.07
     Assoc
    -0.06
    selected
    -0.06
    Sunday
    -0.06
     LOC
    -0.06
    getPath
    -0.06
    .Set
    -0.06
    jumbotron
    -0.06
     Bryant
    -0.06
     mont
    -0.06
    POSITIVE LOGITS
    	label
    0.07
     interest
    0.07
    RAIN
    0.07
     견
    0.07
    etical
    0.06
     teach
    0.06
    FIX
    0.06
     lyn
    0.06
    пов
    0.06
     tweaked
    0.06
    Activations Density 0.021%

    No Known Activations