© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 41502
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens (especially decimal numbers), i.e. it detects number literals 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
    해야
    -0.07
     sha
    -0.07
     ecx
    -0.06
     '':↵
    -0.06
     Dynamics
    -0.06
     AssemblyFileVersion
    -0.06
    -j
    -0.06
     کام
    -0.06
    GridColumn
    -0.06
     beau
    -0.06
    POSITIVE LOGITS
     gestures
    0.07
    (.)
    0.07
     úspě
    0.07
     west
    0.06
    .Style
    0.06
    IU
    0.06
     Keywords
    0.06
    lying
    0.06
    essment
    0.06
     Warm
    0.06
    Activations Density 0.011%

    No Known Activations