© 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. 114054
    Prev
    Next
    INDEX
    Explanations

    online text

    np_max-act · gemini-2.0-flash

    Detects imperative/task-oriented instructions or role/“act as” prompts asking the assistant to perform, improve, or produce something.

    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
    v
    -0.06
    幼
    -0.06
    apiro
    -0.06
    _RANK
    -0.06
    .seconds
    -0.06
    _urls
    -0.06
    ś
    -0.06
     پرداز
    -0.06
    搬
    -0.06
     Ju
    -0.06
    POSITIVE LOGITS
    csv
    0.07
    compiled
    0.07
    >↵↵
    0.06
     horse
    0.06
     performance
    0.06
    -null
    0.06
    .NODE
    0.06
    ificador
    0.06
     dtype
    0.06
     chim
    0.06
    Activations Density 0.069%

    No Known Activations