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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 73232
    Prev
    Next
    INDEX
    Explanations

    knitting

    np_max-act · gemini-2.0-flash
    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
     Бар
    -0.06
     Gü
    -0.06
    tm
    -0.06
    ふ
    -0.06
    рим
    -0.06
     horsepower
    -0.06
     glued
    -0.06
    abcd
    -0.06
     ав
    -0.06
    abcdefgh
    -0.06
    POSITIVE LOGITS
     knitting
    0.08
    foods
    0.08
     centrally
    0.07
                                    ↵
    0.07
     nastav
    0.07
    ting
    0.07
    яття
    0.06
     prominent
    0.06
    -away
    0.06
    CppMethodInitialized
    0.06
    Activations Density 0.011%

    No Known Activations