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. 79697
    Prev
    Next
    INDEX
    Explanations

    code

    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
     nových
    -0.08
     Valle
    -0.07
     Remarks
    -0.07
    (di
    -0.06
     Vision
    -0.06
    919
    -0.06
     Kurd
    -0.06
    ัศ
    -0.06
     Lid
    -0.06
     Wyatt
    -0.06
    POSITIVE LOGITS
     мит
    0.07
    batis
    0.07
    	switch
    0.07
    mac
    0.07
    [--
    0.06
    _action
    0.06
     surrender
    0.06
    در
    0.06
    _Handle
    0.06
     изб
    0.06
    Activations Density 0.036%

    No Known Activations