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. 3-RESID-POST-AA
    6. 122181
    Prev
    Next
    INDEX
    Explanations

    against

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ABILITY
    -0.07
    516
    -0.07
    onyms
    -0.06
     P
    -0.06
    hoa
    -0.06
    liqu
    -0.06
     EU
    -0.06
    brig
    -0.06
    etimes
    -0.06
    LOSS
    -0.06
    POSITIVE LOGITS
     against
    0.12
     Against
    0.12
    against
    0.11
    Against
    0.07
    .setVerticalGroup
    0.07
    .pred
    0.07
     законодатель
    0.07
     العن
    0.07
     більш
    0.07
     навк
    0.07
    Activations Density 0.009%

    No Known Activations