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. 104288
    Prev
    Next
    INDEX
    Explanations

    input tag

    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
     діт
    -0.07
     Accident
    -0.07
     сказав
    -0.07
     Thatcher
    -0.07
    ull
    -0.06
     Lion
    -0.06
     cose
    -0.06
     Gives
    -0.06
     advoc
    -0.06
    .details
    -0.06
    POSITIVE LOGITS
    _USED
    0.06
     kredi
    0.06
    HG
    0.06
    Wrong
    0.06
     články
    0.06
     شدند
    0.06
     County
    0.06
    INavigationController
    0.06
    ارک
    0.06
    imization
    0.05
    Activations Density 0.009%

    No Known Activations