© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 27562
    Prev
    Next
    INDEX
    Explanations

    susp

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ################
    -0.08
     slept
    -0.07
    661
    -0.07
    cname
    -0.07
    .cal
    -0.07
     Bali
    -0.06
     clutch
    -0.06
     cyst
    -0.06
    _FUNC
    -0.06
    score
    -0.06
    POSITIVE LOGITS
    ощ
    0.06
    (Environment
    0.06
     Br
    0.06
    Busy
    0.06
     برق
    0.06
    pan
    0.06
    ΕΧ
    0.06
     H
    0.06
    正确
    0.06
     SAN
    0.06
    Activations Density 0.009%

    No Known Activations