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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 80948
    Prev
    Next
    INDEX
    Explanations

    orifice

    np_max-act · gemini-2.0-flash

    technical descriptions of fluid flow control mechanisms.

    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
    Function
    -0.07
    colour
    -0.07
    าค
    -0.07
    佐
    -0.06
    sylvania
    -0.06
     Chat
    -0.06
     내가
    -0.06
     [{"
    -0.06
    ^n
    -0.06
    BLUE
    -0.06
    POSITIVE LOGITS
     باق
    0.07
    aneous
    0.07
    :::::|
    0.07
     aperture
    0.07
    ings
    0.07
     รอบ
    0.07
    ONY
    0.06
     sleepy
    0.06
    分
    0.06
     StringBuilder
    0.06
    Activations Density 0.014%

    No Known Activations