© 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. 91598
    Prev
    Next
    INDEX
    Explanations

    ilk

    np_max-act · gemini-2.0-flash

    specific references to electrical components or specifications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is detecting numeric tokens containing decimal points (floating-point 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
    ocl
    -0.07
    Editors
    -0.06
    otypical
    -0.06
    visited
    -0.06
    оты
    -0.06
    、ア
    -0.06
    няя
    -0.06
     Louise
    -0.06
    -Re
    -0.06
    jad
    -0.06
    POSITIVE LOGITS
     props
    0.08
     พล
    0.07
     πλη
    0.06
     Phật
    0.06
    패
    0.06
     redesigned
    0.06
     bumps
    0.06
     постеп
    0.06
     carbohydrate
    0.06
     pneum
    0.06
    Activations Density 0.004%

    No Known Activations