© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 68686
    Prev
    Next
    INDEX
    Explanations

    ordering numbers

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens (digits and related punctuation) – in other words, it identifies parts of numbers 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
    iver
    -0.06
    ’
    -0.06
     butcher
    -0.06
     beş
    -0.06
    (video
    -0.06
    environments
    -0.06
    then
    -0.06
     frontier
    -0.06
    갔다
    -0.06
    udios
    -0.06
    POSITIVE LOGITS
    /class
    0.07
    /questions
    0.06
     carte
    0.06
    ้องก
    0.06
    oph
    0.06
     destined
    0.06
    AdapterFactory
    0.06
     trademark
    0.06
    [res
    0.06
    DWORD
    0.06
    Activations Density 0.007%

    No Known Activations