© 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. 7-RESID-POST-AA
    11. 95633
    Prev
    Next
    INDEX
    Explanations

    ane

    np_max-act · gemini-2.0-flash

    chemical compound names, especially hydrocarbon/alkane stems and related chemical tokens.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hed
    -0.08
    іття
    -0.07
     кількість
    -0.07
     flor
    -0.07
    靈
    -0.07
     shredd
    -0.07
    ิศ
    -0.07
     bers
    -0.06
    erm
    -0.06
     Ziel
    -0.06
    POSITIVE LOGITS
    ane
    0.12
    ANE
    0.12
     propane
    0.10
    pane
    0.08
     går
    0.07
     Shane
    0.07
    thane
    0.07
     Bang
    0.07
     crunch
    0.07
     поє
    0.07
    Activations Density 0.006%

    No Known Activations