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. 40451
    Prev
    Next
    INDEX
    Explanations

    punctuation/connectives

    np_max-act · gemini-2.0-flash

    The neuron fires on words describing acts of speaking or questioning (e.g. ask, tell, say).

    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
    анні
    -0.07
    included
    -0.07
    AAA
    -0.07
     veterinarian
    -0.07
     vet
    -0.06
    عت
    -0.06
     özellikleri
    -0.06
    analyze
    -0.06
     mandated
    -0.06
     trained
    -0.06
    POSITIVE LOGITS
    لب
    0.08
     Urs
    0.07
    饭
    0.07
     compliment
    0.07
     upt
    0.07
    MUX
    0.07
     blackjack
    0.06
    _COMP
    0.06
     Bingo
    0.06
    /disc
    0.06
    Activations Density 0.056%

    No Known Activations