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. 130305
    Prev
    Next
    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash

    specific questions and answers related to vehicle operation and maintenance.

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

    The neuron fires on interrogative question openings—tokens like “What,” “When,” “Which,” “is,” etc.—marking the start of a question.

    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
     Milwaukee
    -0.07
     Asp
    -0.07
     inse
    -0.07
     mitochondrial
    -0.06
     Wick
    -0.06
    health
    -0.06
     extend
    -0.06
     Kann
    -0.06
     Sunder
    -0.06
    omer
    -0.06
    POSITIVE LOGITS
     RuntimeObject
    0.07
    =in
    0.07
     jsonObject
    0.06
     컨
    0.06
    -foot
    0.06
    ˘
    0.06
    ँ
    0.06
     �
    0.06
    ны
    0.06
    ublik
    0.06
    Activations Density 0.093%

    No Known Activations