© 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. 42554
    Prev
    Next
    INDEX
    Explanations

    lists and ordering

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens (digits), particularly those denoting dates, times, and other quantities.

    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
     Anat
    -0.07
    imeo
    -0.07
     Celt
    -0.07
     fmt
    -0.07
     unconventional
    -0.07
     봐
    -0.07
     kot
    -0.06
     emotional
    -0.06
     UT
    -0.06
     cutoff
    -0.06
    POSITIVE LOGITS
    .statistics
    0.07
    503
    0.07
     은
    0.06
     actresses
    0.06
     сторін
    0.06
     è
    0.06
    iership
    0.06
    دری
    0.06
    	child
    0.06
    sessionId
    0.06
    Activations Density 0.007%

    No Known Activations