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. 40438
    Prev
    Next
    INDEX
    Explanations

    ature

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of protein denaturation (e.g. “denatured,” “denaturation”).

    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
    947
    -0.07
     기자
    -0.06
    (-
    -0.06
    683
    -0.06
     ITS
    -0.06
    大き
    -0.06
     فعال
    -0.06
    _layers
    -0.06
    spacing
    -0.06
     vyz
    -0.06
    POSITIVE LOGITS
     detain
    0.07
     NI
    0.07
     Natural
    0.07
    unexpected
    0.07
    itty
    0.07
    нки
    0.07
    jp
    0.06
    DN
    0.06
     Denver
    0.06
     Unlock
    0.06
    Activations Density 0.002%

    No Known Activations