Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 130402
    Prev
    Next
    INDEX
    Explanations

    press

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the root “press” (in words like press, pressing, pressurized, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
     Tale
    -0.07
    alaria
    -0.07
     Auswahl
    -0.07
    CUDA
    -0.06
    hat
    -0.06
    /auto
    -0.06
    Ideal
    -0.06
     yogurt
    -0.06
    _cuda
    -0.06
     Dani
    -0.06
    POSITIVE LOGITS
     press
    0.17
     Press
    0.16
    Press
    0.16
     presses
    0.12
    PRESS
    0.12
     pressed
    0.12
     pressing
    0.11
    press
    0.11
     PRESS
    0.10
    ss
    0.09
    Activations Density 0.012%

    No Known Activations