© 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. 15-RESID-POST-AA
    6. 103350
    Prev
    Next
    INDEX
    Explanations

    quotation mark

    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
     ################
    -0.06
    ött
    -0.06
    ENDOR
    -0.06
    ASI
    -0.06
    tracted
    -0.06
     '[
    -0.06
    Footer
    -0.06
    олі
    -0.06
    onz
    -0.06
     vyrob
    -0.06
    POSITIVE LOGITS
    Learn
    0.07
    swap
    0.06
    jump
    0.06
    _remaining
    0.06
    价格
    0.06
    turn
    0.06
     natural
    0.06
     hơi
    0.06
     ук
    0.06
     лов
    0.06
    Activations Density 0.015%

    No Known Activations