© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 13389
    Prev
    Next
    INDEX
    Explanations

    Model/series numbers

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens—especially floating‐point and other number strings—i.e. it spots numerical values in the text.

    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
     Psychiat
    -0.06
    ख
    -0.06
     деся
    -0.06
    栏
    -0.06
     tensor
    -0.06
     cvs
    -0.06
    .dist
    -0.06
     kể
    -0.06
    321
    -0.06
     LINE
    -0.06
    POSITIVE LOGITS
     yıllık
    0.07
     adjustable
    0.06
     Rash
    0.06
    》(
    0.06
    했다
    0.06
    하였다
    0.06
     unpredictable
    0.06
    /YYYY
    0.06
    […
    0.06
    こんにちは
    0.06
    Activations Density 0.008%

    No Known Activations