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. 81106
    Prev
    Next
    INDEX
    Explanations

    of

    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
     enchanted
    -0.07
    _bounds
    -0.07
     Hastings
    -0.06
    ONE
    -0.06
    ión
    -0.06
    斯特
    -0.06
     очеред
    -0.06
    marca
    -0.06
    VERY
    -0.06
     scandals
    -0.06
    POSITIVE LOGITS
     Raptors
    0.07
    uuid
    0.06
    .cornerRadius
    0.06
     Thai
    0.06
     Vegas
    0.06
     nghệ
    0.06
     initialise
    0.06
     şah
    0.06
     />↵↵
    0.06
    mmas
    0.06
    Activations Density 0.000%

    No Known Activations