© 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. 40373
    Prev
    Next
    INDEX
    Explanations

    HTML div elements

    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
    brush
    -0.09
    ung
    -0.08
    .googleapis
    -0.08
    iw
    -0.07
     Wayback
    -0.07
    formik
    -0.07
    ikan
    -0.07
     Enumeration
    -0.07
    egr
    -0.07
    ows
    -0.07
    POSITIVE LOGITS
    ided
    0.08
    nish
    0.07
    s
    0.06
    chet
    0.06
    illisecond
    0.06
    iding
    0.06
    idia
    0.06
    isions
    0.06
    ä¹Ī
    0.06
    idi
    0.06
    Activations Density 0.013%

    No Known Activations