© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 782
    Prev
    Next
    INDEX
    Explanations

    connecting words

    np_max-act · gemini-2.0-flash

    This neuron fires on words referring to sports leadership roles or high-profile team context, especially mentions of “captain” and “team.”

    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
     dreamed
    -0.07
    etermined
    -0.07
     bru
    -0.07
     tutor
    -0.07
     tactile
    -0.06
    ank
    -0.06
     scenarios
    -0.06
     logistical
    -0.06
    елю
    -0.06
     raised
    -0.06
    POSITIVE LOGITS
    ایر
    0.06
    *g
    0.06
    ."),
    0.06
    Labels
    0.06
    	query
    0.06
     trebuie
    0.06
     日期
    0.06
    .Att
    0.06
    	SET
    0.06
    ://"
    0.06
    Activations Density 0.106%

    No Known Activations