© 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. 11-RESID-POST-AA
    11. 77722
    Prev
    Next
    INDEX
    Explanations

    forum posts

    np_max-act · gemini-2.0-flash

    it detects instruction or directive words and other meta-prompt tokens (imperatives like "Please", "Ignore", "Format", "Assume", "Output", etc.) in prompts.

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .endDate
    -0.07
    ,on
    -0.07
     внутр
    -0.06
    ARGE
    -0.06
    达
    -0.06
     Closet
    -0.06
    __,
    -0.06
    .nan
    -0.06
    ΙΚΗ
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     paar
    0.07
     Milli
    0.06
     �
    0.06
    ViewChild
    0.06
    956
    0.06
     mandates
    0.06
    651
    0.06
    픈
    0.06
    인가
    0.06
     Василь
    0.06
    Activations Density 0.163%

    No Known Activations