© 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. 10853
    Prev
    Next
    INDEX
    Explanations

    ro

    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
     해
    -0.07
    _Input
    -0.07
     elm
    -0.07
    ivalent
    -0.07
    송
    -0.06
     hallmark
    -0.06
    kok
    -0.06
    ếu
    -0.06
     refactor
    -0.06
     delim
    -0.06
    POSITIVE LOGITS
    ?↵
    0.07
     предус
    0.06
    )。↵
    0.06
    /popper
    0.06
    Aff
    0.06
    Decision
    0.06
    _gateway
    0.06
     deduct
    0.06
     Spart
    0.06
    MESSAGE
    0.06
    Activations Density 0.148%

    No Known Activations