© 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. 55378
    Prev
    Next
    INDEX
    Explanations

    Fahrenheit

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of temperature units (e.g. “Celsius,” “Fahrenheit”) in conversion or weather‐related contexts.

    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
     Van
    -0.07
     StreamWriter
    -0.06
    _^(
    -0.06
    806
    -0.06
     Consort
    -0.06
    (ci
    -0.06
    _kses
    -0.06
    ��
    -0.06
     прод
    -0.06
     meals
    -0.06
    POSITIVE LOGITS
     hvordan
    0.07
    -Americ
    0.07
     mouseClicked
    0.07
    ควบค
    0.07
    (nullptr
    0.07
     randomized
    0.06
    $model
    0.06
    rawing
    0.06
    TabControl
    0.06
     Gew
    0.06
    Activations Density 0.004%

    No Known Activations