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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 19-RESID-POST-AA
    6. 28432
    Prev
    Next
    INDEX
    Explanations

    teaching lessons

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ведите
    -0.06
    esp
    -0.06
     експ
    -0.06
     آش
    -0.06
    (strpos
    -0.06
     Plumbing
    -0.06
    DW
    -0.06
     Presence
    -0.06
     Summers
    -0.06
     instincts
    -0.06
    POSITIVE LOGITS
    llum
    0.07
     TURN
    0.07
    .C
    0.07
    jed
    0.06
     çalışmaları
    0.06
    =*/
    0.06
    (FLAGS
    0.06
    RARY
    0.06
    )').
    0.06
    .nii
    0.06
    Activations Density 0.049%

    No Known Activations