© 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. 39131
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron fires on degree- or magnitude-marking adjective/adverb phrases (e.g. “high incidence,” “still one of the largest,” “possibly in talks”).

    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
     vieille
    -0.07
    Their
    -0.06
     Acres
    -0.06
    iov
    -0.06
    their
    -0.06
    há
    -0.06
    ような
    -0.06
     Venezuelan
    -0.06
    ManyToOne
    -0.06
     onemocnění
    -0.06
    POSITIVE LOGITS
    _;↵
    0.07
     Tile
    0.07
     justify
    0.07
     antig
    0.07
    WH
    0.06
     md
    0.06
    hasClass
    0.06
     EP
    0.06
     इक
    0.06
    	connection
    0.06
    Activations Density 0.147%

    No Known Activations