© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126223
    Prev
    Next
    INDEX
    Explanations

    run

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens, especially decimal numbers and other number-like strings.

    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
    _bits
    -0.07
     ступ
    -0.07
    	frame
    -0.07
     صنایع
    -0.07
    471
    -0.06
    versation
    -0.06
    _request
    -0.06
     "&#
    -0.06
     label
    -0.06
     کیفیت
    -0.06
    POSITIVE LOGITS
     Runs
    0.07
     Attend
    0.07
    nn
    0.07
     flying
    0.06
    ريد
    0.06
     Zur
    0.06
    mn
    0.06
     =↵↵
    0.06
     sessions
    0.06
     CLI
    0.06
    Activations Density 0.040%

    No Known Activations