© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 57284
    Prev
    Next
    INDEX
    Explanations

    words related to menu structures in programming or software contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pour
    -0.07
    csi
    -0.07
    ped
    -0.07
    toolbox
    -0.07
    ment
    -0.07
    uzzi
    -0.07
    g
    -0.07
    rias
    -0.07
    اØŃت
    -0.07
    ลล
    -0.07
    POSITIVE LOGITS
    stration
    0.10
    item
    0.10
    ìĸ¼
    0.08
    items
    0.08
    Items
    0.08
    onder
    0.07
    isphere
    0.07
     items
    0.07
    itemid
    0.07
    -item
    0.07
    Activations Density 0.009%

    No Known Activations