© 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. 126211
    Prev
    Next
    INDEX
    Explanations

    numbers and lists

    np_max-act · gemini-2.0-flash

    This neuron detects numeric count tokens (digits or number words) that specify quantities (e.g. “3,” “three,” “scenes,” “per”) in an outline.

    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
    =True
    -0.06
     SPE
    -0.06
    iegel
    -0.06
     ste
    -0.06
    Unsafe
    -0.06
     따
    -0.06
    :description
    -0.06
     μα
    -0.06
    Die
    -0.06
     SOAP
    -0.06
    POSITIVE LOGITS
    |#
    0.07
    λικ
    0.06
     طب
    0.06
     dejar
    0.06
    찬
    0.06
     intensely
    0.06
    699
    0.06
     -,
    0.06
    ोफ
    0.06
    正式
    0.06
    Activations Density 0.066%

    No Known Activations