© 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. 91925
    Prev
    Next
    INDEX
    Explanations

    code or abstracts

    np_max-act · gemini-2.0-flash

    The neuron activates on standalone single uppercase letters (e.g. “C”, “T”, “H”, “D”) 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
     Ross
    -0.08
     Mart
    -0.07
     DAT
    -0.06
     wget
    -0.06
     INNER
    -0.06
     Lund
    -0.06
     apo
    -0.06
     Costa
    -0.06
     Jenna
    -0.06
     Saves
    -0.06
    POSITIVE LOGITS
    (version
    0.07
     (($
    0.07
    ازد
    0.07
    (frame
    0.07
    (BitConverter
    0.07
    ($
    0.07
    (S
    0.06
    (background
    0.06
     aud
    0.06
    igmat
    0.06
    Activations Density 0.015%

    No Known Activations