© 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. 90647
    Prev
    Next
    INDEX
    Explanations

    dash

    np_max-act · gemini-2.0-flash

    The neuron activates on floating-point numeric literals (decimal numbers) in code.

    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
    CLAIM
    -0.07
     �
    -0.07
     Kis
    -0.07
    divid
    -0.06
    	cache
    -0.06
    須
    -0.06
     millet
    -0.06
    Điều
    -0.06
     mist
    -0.06
     weed
    -0.06
    POSITIVE LOGITS
     dB
    0.07
     благодаря
    0.06
     dlouh
    0.06
    ῦ
    0.06
    Longitude
    0.06
    _CHANGED
    0.06
     говорит
    0.06
    ώνα
    0.06
     přibliž
    0.06
    _NAMESPACE
    0.06
    Activations Density 0.005%

    No Known Activations