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. 22416
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    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
    Msg
    -0.06
    .text
    -0.06
     =================================================
    -0.06
    =${
    -0.06
    िय
    -0.06
     FUCK
    -0.06
     PRINT
    -0.06
     Tep
    -0.06
    됨
    -0.06
     anarchist
    -0.06
    POSITIVE LOGITS
     gratuite
    0.07
    ール
    0.07
     roasted
    0.06
    mods
    0.06
    ĩnh
    0.06
    ='./
    0.06
    Neutral
    0.06
     happily
    0.06
     skl
    0.06
    /es
    0.06
    Activations Density 0.009%

    No Known Activations