© 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. 110182
    Prev
    Next
    INDEX
    Explanations

    –

    np_max-act · gemini-2.0-flash

    The neuron is tuned to spotting numeric tokens with decimal points (i.e. the fractional parts of dates or other numbers).

    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
    _Play
    -0.07
    'y
    -0.06
    ourcing
    -0.06
     dispos
    -0.06
     conductor
    -0.06
    }'
    -0.06
     puck
    -0.06
    Fit
    -0.06
    Lin
    -0.06
     της
    -0.06
    POSITIVE LOGITS
    _cre
    0.06
     tüm
    0.06
    	rb
    0.06
     soru
    0.06
    ‐-
    0.06
    іш
    0.06
    eleri
    0.06
    άνι
    0.06
    .uri
    0.06
    ивают
    0.06
    Activations Density 0.004%

    No Known Activations