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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 121992
    Prev
    Next
    INDEX
    Explanations

    something is too low

    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
     RESOURCE
    -0.07
     summ
    -0.07
     injector
    -0.06
     mdi
    -0.06
    (MPI
    -0.06
     lượng
    -0.06
    Connected
    -0.06
     Aç
    -0.06
     fighters
    -0.06
    .accuracy
    -0.06
    POSITIVE LOGITS
    �
    0.07
     всё
    0.06
    рем
    0.06
     compt
    0.06
    nie
    0.06
    .Cascade
    0.06
    getPage
    0.06
     eine
    0.06
    -West
    0.06
    *t
    0.06
    Activations Density 0.145%

    No Known Activations