© 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. 40145
    Prev
    Next
    INDEX
    Explanations

    of

    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
     unfolding
    -0.07
     outfit
    -0.06
     Rodney
    -0.06
     CLL
    -0.06
    :h
    -0.06
     DTO
    -0.06
    ωδ
    -0.06
    /os
    -0.06
    ню
    -0.06
     Graph
    -0.06
    POSITIVE LOGITS
     ženy
    0.07
     Marks
    0.07
    品牌
    0.07
    ensagem
    0.06
     Advances
    0.06
     제목
    0.06
    _CHAN
    0.06
    Britain
    0.06
    ivil
    0.06
    ,unsigned
    0.06
    Activations Density 0.083%

    No Known Activations