© 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. 11-RESID-POST-AA
    6. 69306
    Prev
    Next
    INDEX
    Explanations

    controversies

    np_max-act · gemini-2.0-flash

    mentions of public statements or communications in news-style reporting, especially social media posts, quoted remarks, and reporting verbs indicating someone said or called something.

    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_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
    iku
    -0.07
    PLUS
    -0.07
     yeme
    -0.06
    цен
    -0.06
    LEX
    -0.06
    速度
    -0.06
     rừng
    -0.06
     Experienced
    -0.06
     Integrity
    -0.06
     Cuomo
    -0.06
    POSITIVE LOGITS
    .Ver
    0.09
     different
    0.06
    <K
    0.06
    	HAL
    0.06
     DESC
    0.06
     biliyor
    0.06
     sáng
    0.06
     onclick
    0.06
    [OF
    0.06
    |(↵
    0.06
    Activations Density 0.139%

    No Known Activations