© 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. 41573
    Prev
    Next
    INDEX
    Explanations

    many

    np_max-act · gemini-2.0-flash

    This neuron detects decimal numbers (floating‐point values) embedded 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
    -touch
    -0.07
    .BorderFactory
    -0.06
    atte
    -0.06
     �
    -0.06
    subst
    -0.06
    omat
    -0.06
    914
    -0.06
     практически
    -0.06
     München
    -0.06
     розгля
    -0.06
    POSITIVE LOGITS
    ([])↵
    0.07
     companyId
    0.07
    _sid
    0.06
     [],↵
    0.06
     Tay
    0.06
     newPath
    0.06
    .Created
    0.06
    mite
    0.06
    (id
    0.06
    Or
    0.06
    Activations Density 0.010%

    No Known Activations