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. 121967
    Prev
    Next
    INDEX
    Explanations

    thick

    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
    &apos
    -0.08
    owards
    -0.07
    .any
    -0.07
     rites
    -0.06
    FirstOrDefault
    -0.06
    'aut
    -0.06
     Around
    -0.06
     vận
    -0.06
     aimed
    -0.06
    ายใน
    -0.06
    POSITIVE LOGITS
     thick
    0.10
     Thick
    0.09
     heavy
    0.08
     Shark
    0.07
     thicker
    0.07
    (profile
    0.06
     McC
    0.06
     Brook
    0.06
     corporations
    0.06
    _X
    0.06
    Activations Density 0.015%

    No Known Activations