Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 123176
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of food and drink items (and their quantities) in lists or recipe-style contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    dishes that can be paired with specific drinks.

    oai_token-act-pair · gpt-4o-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
    絡
    -0.07
    /mock
    -0.06
     wary
    -0.06
     effective
    -0.06
    .zz
    -0.06
    effective
    -0.06
    _within
    -0.06
    /INFO
    -0.06
    대비
    -0.06
    денти
    -0.06
    POSITIVE LOGITS
     ';
    0.07
     extended
    0.07
    >';
    0.06
     scoped
    0.06
     yapan
    0.06
    -Un
    0.06
    getData
    0.06
    "';
    0.06
    联盟
    0.06
    (dec
    0.06
    Activations Density 0.056%

    No Known Activations