© 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. 84323
    Prev
    Next
    INDEX
    Explanations

    references to significant events or dates

    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
    REFERRED
    -0.08
    inis
    -0.08
    sein
    -0.07
    ials
    -0.07
    SSION
    -0.07
    arend
    -0.07
    ASI
    -0.06
    enade
    -0.06
    tere
    -0.06
    seo
    -0.06
    POSITIVE LOGITS
    eenth
    0.08
    urement
    0.08
    edly
    0.07
    GetObject
    0.07
    -ÑĤаки
    0.07
    ihar
    0.07
    een
    0.07
    aby
    0.06
    YLES
    0.06
    hips
    0.06
    Activations Density 0.046%

    No Known Activations