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. 81440
    Prev
    Next
    INDEX
    Explanations

    Reaching a climax/culmination

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the verb “culminate” (in any of its inflected forms such as “culminated” or “culminating”).

    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
     appar
    -0.06
    _specs
    -0.06
     إلى
    -0.06
     이러한
    -0.06
     liberalism
    -0.06
     Bern
    -0.06
     nuevos
    -0.06
    erge
    -0.06
     pageable
    -0.06
    lds
    -0.06
    POSITIVE LOGITS
     culmination
    0.09
     climax
    0.08
     заверш
    0.08
     clim
    0.08
    輝
    0.07
     Shall
    0.07
     cul
    0.07
    minating
    0.07
    mouseup
    0.07
     CLUB
    0.07
    Activations Density 0.007%

    No Known Activations