© 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. 30548
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric tokens (constants) in the equations—that is, it fires on numbers.

    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
    -wide
    -0.07
     argue
    -0.07
     SHIFT
    -0.07
    (now
    -0.06
     Stainless
    -0.06
     vast
    -0.06
    _HEAD
    -0.06
     Total
    -0.06
     GRAPH
    -0.06
    IGNORE
    -0.06
    POSITIVE LOGITS
     bozuk
    0.06
     خیابان
    0.06
     şans
    0.06
    .articles
    0.06
     sweetness
    0.06
     kolay
    0.06
    	↵↵
    0.06
    0.06
    uridad
    0.06
    getDisplay
    0.06
    Activations Density 0.008%

    No Known Activations