© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 84585
    Prev
    Next
    INDEX
    Explanations

    pronouns

    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
    _salt
    -0.07
     elucid
    -0.07
     dat
    -0.07
     أن
    -0.06
    规划
    -0.06
    compose
    -0.06
     naveg
    -0.06
    ाइस
    -0.06
    에서의
    -0.06
    uddy
    -0.06
    POSITIVE LOGITS
    となり
    0.07
    手机号
    0.06
     emptied
    0.06
    embedded
    0.06
    <=$
    0.05
     Unsafe
    0.05
    <k
    0.05
     abducted
    0.05
    agedList
    0.05
    graded
    0.05
    Activations Density 0.070%

    No Known Activations