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. 764
    Prev
    Next
    INDEX
    Explanations

    No meaningful content

    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
    사가
    -0.07
    wią
    -0.07
    ์พ
    -0.06
    ПО
    -0.06
     rozs
    -0.06
    (ln
    -0.06
     itemId
    -0.06
    blend
    -0.06
    bar
    -0.06
    )>=
    -0.06
    POSITIVE LOGITS
     hindsight
    0.07
    _lead
    0.06
    possible
    0.06
    ฬ
    0.06
     '~
    0.06
    """
    ↵
    ↵
    0.06
     деятельности
    0.06
     Future
    0.05
     winnings
    0.05
     Familie
    0.05
    Activations Density 0.007%

    No Known Activations