© 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. 46934
    Prev
    Next
    INDEX
    Explanations

    benign

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on the adjective “benign,” i.e. it detects occurrences of “benign” in medical descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    terms related to benign tumors and their descriptions in medical contexts.

    oai_token-act-pair · gpt-4o-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
     голов
    -0.07
    ucht
    -0.07
    alance
    -0.06
     precip
    -0.06
     jedoch
    -0.06
     wła
    -0.06
     hardcore
    -0.06
    gross
    -0.06
    �
    -0.06
     Dollars
    -0.06
    POSITIVE LOGITS
     benign
    0.10
    ToolStripMenuItem
    0.07
    Indexed
    0.06
    Visibility
    0.06
    <"
    0.06
    enor
    0.06
     Bri
    0.06
    ivor
    0.06
     amor
    0.06
    :+
    0.06
    Activations Density 0.002%

    No Known Activations