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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30705
    Prev
    Next
    INDEX
    Explanations

    umor

    np_max-act · gemini-2.0-flash

    keywords associated with tumor biology and immunotherapy.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron primarily activates on the word “tumor,” signaling mentions of tumors in biomedical text.

    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
    カテ
    -0.07
    งเศ
    -0.07
    ESİ
    -0.07
    เ
    -0.07
    ASI
    -0.07
     relay
    -0.07
    cery
    -0.07
    PHY
    -0.07
    ASY
    -0.07
    ane
    -0.07
    POSITIVE LOGITS
     tumor
    0.15
     tumors
    0.13
     tum
    0.10
     rumored
    0.09
     rumor
    0.08
    um
    0.08
    umor
    0.08
     Um
    0.08
    ur
    0.08
     rumors
    0.08
    Activations Density 0.013%

    No Known Activations