Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 52056
    Prev
    Next
    INDEX
    Explanations

    Q

    np_max-act · gemini-2.0-flash

    HTML and JavaScript structural elements used in web development documents.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    tokens that are part of markup/structural document tags (HTML/XML‑style tags and other structural delimiters).

    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
    Dim
    -0.06
     packaged
    -0.06
    imuth
    -0.06
    اهيم
    -0.06
     createElement
    -0.06
     cow
    -0.06
    LINK
    -0.06
     Pig
    -0.06
     furn
    -0.06
     splice
    -0.06
    POSITIVE LOGITS
     OnCollision
    0.07
    _GRE
    0.06
    .toUpperCase
    0.06
     Crimea
    0.06
     ทอง
    0.06
     vừa
    0.06
    surname
    0.06
    _wrap
    0.06
    .setName
    0.06
     learners
    0.06
    Activations Density 0.317%

    No Known Activations