Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-RESID-POST-AA
    6. 54449
    Prev
    Next
    INDEX
    Explanations

    {

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    極
    -0.08
    antan
    -0.06
     Mut
    -0.06
     kể
    -0.06
    ì
    -0.06
    WillAppear
    -0.06
     miserable
    -0.06
    dll
    -0.06
    .API
    -0.06
    prox
    -0.06
    POSITIVE LOGITS
     лікар
    0.07
     Collision
    0.07
     Ges
    0.06
    .rotate
    0.06
     numer
    0.06
    "People
    0.06
    theses
    0.06
    spd
    0.06
     collision
    0.06
    Cancelar
    0.06
    Activations Density 0.030%

    No Known Activations