Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 125833
    Prev
    Next
    INDEX
    Explanations

    divisibility checks

    np_max-act · gemini-2.0-flash

    The neuron activates specifically on numeric tokens (multi‐digit integers) within arithmetic questions.

    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
     bloque
    -0.07
     detected
    -0.07
     Stefan
    -0.06
    .SQLite
    -0.06
     llama
    -0.06
    elter
    -0.06
     TTC
    -0.06
     burial
    -0.06
     Comcast
    -0.06
    	address
    -0.06
    POSITIVE LOGITS
    IOD
    0.07
    claim
    0.07
    :SetPoint
    0.06
    .setPosition
    0.06
    States
    0.06
     arrests
    0.06
    _LAST
    0.06
    owanie
    0.06
     drink
    0.06
    cash
    0.06
    Activations Density 0.014%

    No Known Activations