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. 81065
    Prev
    Next
    INDEX
    Explanations

    exist

    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
    ompson
    -0.08
     Pump
    -0.08
     mark
    -0.07
     Thompson
    -0.07
     Beam
    -0.07
     Campbell
    -0.07
     Make
    -0.07
     mamma
    -0.07
    -per
    -0.07
     bumps
    -0.07
    POSITIVE LOGITS
     exist
    0.14
     exists
    0.13
     existed
    0.12
     Exists
    0.10
    Exists
    0.09
    exist
    0.09
    .exists
    0.09
     Exist
    0.09
     existing
    0.08
    Exist
    0.08
    Activations Density 0.033%

    No Known Activations