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. 21801
    Prev
    Next
    INDEX
    Explanations

    Numbers, especially 0 and 10

    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
     Matlab
    -0.06
    			       
    -0.06
    .Target
    -0.06
     cms
    -0.06
     branches
    -0.06
     Increment
    -0.06
     прибы
    -0.06
    actors
    -0.06
     Fluid
    -0.06
     Walker
    -0.06
    POSITIVE LOGITS
    habit
    0.07
    Arduino
    0.07
    claim
    0.07
    suspend
    0.06
    perms
    0.06
    ुछ
    0.06
     apa
    0.06
    ैं.↵
    0.06
    orderId
    0.06
     zaten
    0.06
    Activations Density 0.005%

    No Known Activations