© 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. 91949
    Prev
    Next
    INDEX
    Explanations

    code examples

    np_max-act · gemini-2.0-flash

    This neuron fires on standalone action verbs (present-tense commands) in the text.

    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
     addButton
    -0.08
     listed
    -0.08
     contour
    -0.07
    935
    -0.07
     skepticism
    -0.07
     contours
    -0.07
     Maker
    -0.06
    434
    -0.06
     Born
    -0.06
    кости
    -0.06
    POSITIVE LOGITS
    いた
    0.06
    Oracle
    0.06
    :self
    0.06
     copper
    0.06
     Literal
    0.06
     živ
    0.06
    ergisi
    0.06
     vů
    0.06
    vertisement
    0.06
    �
    0.06
    Activations Density 0.083%

    No Known Activations