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. 86151
    Prev
    Next
    INDEX
    Explanations

    exhibit

    np_max-act · gemini-2.0-flash

    The neuron activates on the verb “exhibit” (and its inflected forms like “exhibits,” “exhibited,” etc.), i.e. instances of that specific display/present verb.

    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
     tired
    -0.08
     care
    -0.07
    (right
    -0.07
     Age
    -0.07
     sense
    -0.07
     Failed
    -0.07
     Nr
    -0.07
    _Command
    -0.07
    ^K
    -0.07
     Mary
    -0.07
    POSITIVE LOGITS
     exhibited
    0.11
     exhibiting
    0.10
     exhibit
    0.09
     Exhib
    0.08
    wayne
    0.08
     exempl
    0.08
     exhib
    0.08
     exhibits
    0.07
     할
    0.07
    显
    0.07
    Activations Density 0.009%

    No Known Activations