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. 100481
    Prev
    Next
    INDEX
    Explanations

    tragedy

    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
    _button
    -0.07
    _int
    -0.06
     gamers
    -0.06
     Walters
    -0.06
     diets
    -0.06
    gien
    -0.06
     repercussions
    -0.06
     роб
    -0.06
    	background
    -0.06
    Bern
    -0.06
    POSITIVE LOGITS
     tragic
    0.12
     tragedy
    0.11
     tragedies
    0.10
     trag
    0.08
     traged
    0.08
    ph
    0.08
     venture
    0.08
     ถ
    0.07
     záz
    0.07
    fortune
    0.07
    Activations Density 0.006%

    No Known Activations