© 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. 69189
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    references to birthday-related topics and party planning ideas.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
     tức
    -0.07
     chí
    -0.07
    ิ
    -0.06
    ा.↵
    -0.06
    ///////////////////////////////////////////////////////////////////////////////↵
    -0.06
    posure
    -0.06
     Leone
    -0.06
     territory
    -0.06
    urus
    -0.06
    244
    -0.06
    POSITIVE LOGITS
    olid
    0.06
     jdbc
    0.06
     فو
    0.06
    이터
    0.06
     BaseController
    0.06
     litt
    0.06
     MATERIAL
    0.06
    ertz
    0.06
     Retrieve
    0.06
     feminist
    0.05
    Activations Density 0.445%

    No Known Activations