© 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. 7-RESID-POST-AA
    6. 46501
    Prev
    Next
    INDEX
    Explanations

    Questions

    np_max-act · gemini-2.0-flash

    direct questions to the interlocutor in dialogue, especially auxiliary- or wh-led prompts seeking information or confirmation.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Hand
    -0.07
     consultar
    -0.07
    極
    -0.07
    Containing
    -0.07
     характеристики
    -0.07
     differently
    -0.07
     yaklaşık
    -0.06
    ’int
    -0.06
    ぬ
    -0.06
     immersion
    -0.06
    POSITIVE LOGITS
    /***************************************************************************↵
    0.06
     complement
    0.06
    .VisibleIndex
    0.06
    :'.$
    0.06
     PageInfo
    0.06
    findBy
    0.06
     �
    0.06
    Asian
    0.06
    Translations
    0.06
    farm
    0.06
    Activations Density 0.088%

    No Known Activations