© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68746
    Prev
    Next
    INDEX
    Explanations

    thick

    np_max-act · gemini-2.0-flash

    The neuron activates on words that describe the thickening of a sauce or stew (e.g., “thick,” “thickened,” “ens”).

    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
     Biol
    -0.07
     vurgu
    -0.06
     dương
    -0.06
     Giáo
    -0.06
    قف
    -0.06
     Однак
    -0.06
    "},"
    -0.06
     однако
    -0.06
    (dest
    -0.06
     MDMA
    -0.06
    POSITIVE LOGITS
    -heading
    0.07
    /high
    0.07
     assure
    0.06
     authorize
    0.06
     indian
    0.06
    complexContent
    0.06
     kém
    0.06
    Accept
    0.06
     Short
    0.06
    31
    0.06
    Activations Density 0.003%

    No Known Activations