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. 84420
    Prev
    Next
    INDEX
    Explanations

    find

    np_max-act · gemini-2.0-flash

    mathematical operations related to derivatives.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on floating‐point numeric literals (numbers containing a decimal point).

    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
     加
    -0.07
    加
    -0.07
     licz
    -0.06
     numero
    -0.06
     Compar
    -0.06
     salsa
    -0.06
     Wong
    -0.06
     comparative
    -0.06
     Sweet
    -0.06
    anagan
    -0.06
    POSITIVE LOGITS
    ुन
    0.07
     fread
    0.07
    _duplicates
    0.07
    <Guid
    0.06
    RenderWindow
    0.06
    .done
    0.06
    .openqa
    0.06
    	Destroy
    0.06
     madrid
    0.06
    ốt
    0.06
    Activations Density 0.002%

    No Known Activations