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. 15-RESID-POST-AA
    6. 12037
    Prev
    Next
    INDEX
    Explanations

    older

    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
     Hubb
    -0.06
    _config
    -0.06
     JNI
    -0.06
     touching
    -0.06
    127
    -0.06
    _ans
    -0.06
    quisite
    -0.06
    ivate
    -0.06
     labyrinth
    -0.06
    (btn
    -0.06
    POSITIVE LOGITS
     older
    0.08
     Older
    0.08
    .userAgent
    0.07
    더
    0.07
     Interr
    0.07
    color
    0.07
     refill
    0.07
    :NO
    0.06
     Organizer
    0.06
    ":[{"
    0.06
    Activations Density 0.005%

    No Known Activations