Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 110570
    Prev
    Next
    INDEX
    Explanations

    one them

    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
     sof
    -0.07
     recur
    -0.07
    (widget
    -0.06
    Deleted
    -0.06
    -largest
    -0.06
    cd
    -0.06
    isObject
    -0.06
     레벨
    -0.06
    )a
    -0.06
    Density
    -0.06
    POSITIVE LOGITS
     ellos
    0.07
     just
    0.06
    _man
    0.06
    IN
    0.06
    承
    0.06
     installment
    0.06
    ียง
    0.06
    用品
    0.06
    WN
    0.06
     UNDER
    0.06
    Activations Density 0.019%

    No Known Activations