© 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. 55884
    Prev
    Next
    INDEX
    Explanations

    actually

    np_max-act · gemini-2.0-flash

    This neuron fires on self-referential opinion words—especially the pronoun “I” and emphasis words like “actually” or “definitely” indicating personal commentary.

    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
    forums
    -0.06
    xCE
    -0.06
    perience
    -0.06
    mium
    -0.06
    IPHER
    -0.06
    tiği
    -0.06
     comparative
    -0.06
    {!!
    -0.06
     Zero
    -0.06
    .GridColumn
    -0.06
    POSITIVE LOGITS
     actually
    0.13
    actually
    0.08
     arguably
    0.08
     eigentlich
    0.08
     dành
    0.08
     �
    0.08
     Actually
    0.08
    typically
    0.07
     chevy
    0.07
     democr
    0.07
    Activations Density 0.016%

    No Known Activations