© 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
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 93437
    Prev
    Next
    INDEX
    Explanations

    ative

    np_max-act · gemini-2.0-flash

    words or subword pieces starting with "gener" (e.g., "Generative"/"generate") especially in the phrase "Generative Pre-trained Transformer" (GPT).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     ifs
    -0.07
     NaN
    -0.06
     铁
    -0.06
     medicinal
    -0.06
     Ortiz
    -0.06
     Ра
    -0.06
     inequalities
    -0.06
    NaN
    -0.06
    dropIfExists
    -0.06
    _eta
    -0.06
    POSITIVE LOGITS
    ++++
    0.07
     regimes
    0.06
     ).
    0.06
    ANDING
    0.06
    ;-
    0.06
    CASE
    0.06
    economic
    0.06
     martial
    0.06
    iv
    0.06
     regime
    0.06
    Activations Density 0.004%

    No Known Activations