© 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. 73604
    Prev
    Next
    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash

    The neuron activates on the asterisk character (“*”), flagging occurrences of that symbol (often used for emphasis, footnotes, or list markers).

    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
     Conn
    -0.08
     nen
    -0.08
    ureen
    -0.08
     resilience
    -0.07
     Hein
    -0.07
     Cohen
    -0.07
    NI
    -0.07
    rien
    -0.07
     повин
    -0.07
     remin
    -0.07
    POSITIVE LOGITS
     *
    0.11
    *
    0.10
    (*
    0.09
     (*
    0.09
    *,
    0.09
    ast
    0.09
     '*
    0.08
    ack
    0.08
    _*
    0.08
    AK
    0.08
    Activations Density 0.152%

    No Known Activations