© 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. 91676
    Prev
    Next
    INDEX
    Explanations

    creating

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens, especially decimal numbers and other numeric values.

    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
    intree
    -0.07
     deepen
    -0.07
    Dia
    -0.06
    히
    -0.06
     Bik
    -0.06
    بینی
    -0.06
    _mobile
    -0.06
     isAdmin
    -0.06
     tears
    -0.06
    ')}}">
    -0.06
    POSITIVE LOGITS
    	del
    0.08
     탈
    0.07
    .Bytes
    0.06
     komp
    0.06
     réalis
    0.06
    151
    0.06
    (init
    0.06
    ATHER
    0.06
    _EOL
    0.06
     Created
    0.06
    Activations Density 0.041%

    No Known Activations