© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44260
    Prev
    Next
    INDEX
    Explanations

    sandwiches and restaurants

    np_max-act · gemini-2.0-flash

    The neuron flags menu-related text—especially item names and listings in a restaurant’s menu section.

    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
     searchString
    -0.07
     Agricultural
    -0.07
    imag
    -0.07
    Humans
    -0.07
     Press
    -0.06
    .ReadAll
    -0.06
    antages
    -0.06
     bzw
    -0.06
     anus
    -0.06
    nov
    -0.06
    POSITIVE LOGITS
     Modify
    0.06
    (RE
    0.06
    　l
    0.06
    گونه
    0.06
     рассчит
    0.06
    िनट
    0.06
     empower
    0.06
    createdAt
    0.06
     μέχρι
    0.06
    ็ต
    0.06
    Activations Density 0.026%

    No Known Activations