© 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. 57988
    Prev
    Next
    INDEX
    Explanations

    lists

    np_max-act · gemini-2.0-flash

    The neuron is specialized to detect section headings (short title labels) in the document.

    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
    put
    -0.07
     educating
    -0.07
    	input
    -0.07
    Complete
    -0.07
    024
    -0.06
    Input
    -0.06
    atre
    -0.06
    abant
    -0.06
    DataManager
    -0.06
     öğretmen
    -0.06
    POSITIVE LOGITS
     lodged
    0.07
     noop
    0.07
    \Catalog
    0.06
    roadcast
    0.06
    سنگ
    0.06
    zx
    0.06
    _JOIN
    0.06
     arab
    0.06
    лит
    0.06
    lico
    0.06
    Activations Density 0.051%

    No Known Activations