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. 15-RESID-POST-AA
    6. 79962
    Prev
    Next
    INDEX
    Explanations

    recipes

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Recipe
    -0.07
     eating
    -0.07
     Funding
    -0.06
     Hair
    -0.06
    jj
    -0.06
    obby
    -0.06
    SEQ
    -0.06
     katı
    -0.06
    spell
    -0.06
     track
    -0.06
    POSITIVE LOGITS
     Nelson
    0.07
    менш
    0.07
    nuts
    0.06
    	RTHOOK
    0.06
    imizi
    0.06
    ANDOM
    0.06
    もっと
    0.06
    ну
    0.06
    译
    0.06
    vements
    0.06
    Activations Density 0.026%

    No Known Activations