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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 57764
    Prev
    Next
    INDEX
    Explanations

    much

    np_max-act · gemini-2.0-flash

    This neuron detects degree‐modifier adverbs (intensifiers) such as “much” and “more.”

    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
    î
    -0.08
     i
    -0.08
    ΙΔ
    -0.07
     tier
    -0.07
    idis
    -0.07
    ii
    -0.07
    bere
    -0.07
    -i
    -0.07
     Nir
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     much
    0.11
     Much
    0.10
    Much
    0.10
     MUCH
    0.10
    much
    0.09
    $scope
    0.08
    ocom
    0.07
     excess
    0.07
    .Wh
    0.07
    .What
    0.07
    Activations Density 0.017%

    No Known Activations