© 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
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 128995
    Prev
    Next
    INDEX
    Explanations

    code

    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
     philosophers
    -0.07
    _,,
    -0.06
    Map
    -0.06
    保護
    -0.06
     rychle
    -0.06
     Its
    -0.06
    Graphics
    -0.06
    �
    -0.06
     Those
    -0.06
     $
    -0.06
    POSITIVE LOGITS
     �
    0.08
    危
    0.06
    _worker
    0.06
     bewild
    0.06
     werk
    0.06
    َو
    0.06
     oben
    0.06
     zd
    0.06
     ent
    0.06
     رقم
    0.06
    Activations Density 0.048%

    No Known Activations