© 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. 7011
    Prev
    Next
    INDEX
    Explanations

    updates and news

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens with 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
     Morton
    -0.07
     Perkins
    -0.07
     orth
    -0.06
     microscope
    -0.06
    ensible
    -0.06
    -base
    -0.06
    (depth
    -0.06
     Compar
    -0.06
     Brent
    -0.06
    '*
    -0.06
    POSITIVE LOGITS
    tvrt
    0.06
     disadv
    0.06
    ोड़
    0.06
    attle
    0.06
    .middleware
    0.06
     mention
    0.06
     nêu
    0.06
     万円
    0.06
    iddled
    0.06
     لإ
    0.06
    Activations Density 0.057%

    No Known Activations