© 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 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. 37975
    Prev
    Next
    INDEX
    Explanations

    difference

    np_max-act · gemini-2.0-flash

    The neuron activates on the word “difference,” i.e. when the text is making a comparison or highlighting a distinction.

    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
     UPDATED
    -0.07
    alama
    -0.06
    UserCode
    -0.06
    DEBUG
    -0.06
    Paginator
    -0.06
    ales
    -0.06
    termination
    -0.06
    ateurs
    -0.06
    [email
    -0.06
     Maryland
    -0.06
    POSITIVE LOGITS
     difference
    0.08
     differs
    0.08
     differences
    0.07
     Differences
    0.06
    0.06
    ,color
    0.06
     warmth
    0.06
     она
    0.06
     nga
    0.06
    -storage
    0.06
    Activations Density 0.025%

    No Known Activations