© 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. 126283
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron is tuned to detect numeric expressions—especially decimal numbers, percentages, and other quantitative figures.

    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
     Tablet
    -0.07
    atonin
    -0.07
    Lv
    -0.07
     Schiff
    -0.06
     Tween
    -0.06
     Lyme
    -0.06
    Ci
    -0.06
    Boot
    -0.06
     Levine
    -0.06
     Carpenter
    -0.06
    POSITIVE LOGITS
     participating
    0.06
    σαν
    0.06
     employed
    0.06
    ={}↵
    0.06
     requires
    0.06
    )).↵
    0.06
    .",
↵
    0.06
     convenience
    0.06
    Interested
    0.06
    /all
    0.06
    Activations Density 0.027%

    No Known Activations