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. 3-RESID-POST-AA
    6. 94445
    Prev
    Next
    INDEX
    Explanations

    but

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     З
    -0.07
    *****
    -0.06
     celou
    -0.06
     plantation
    -0.06
    holding
    -0.06
    Palindrome
    -0.06
     displaced
    -0.06
     ogl
    -0.06
     Indicator
    -0.06
    tol
    -0.06
    POSITIVE LOGITS
    [${
    0.07
     시작
    0.06
    (types
    0.06
    術
    0.06
     firstly
    0.06
     emot
    0.06
     thiết
    0.06
    .After
    0.06
     func
    0.06
     зрозум
    0.06
    Activations Density 0.086%

    No Known Activations