© 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 EvalsExportsinterp-engineNEWAPI 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. 119759
    Prev
    Next
    INDEX
    Explanations

    opportunities and choices related to support, security, and future options

    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
    igne
    -0.07
    mans
    -0.06
     gros
    -0.06
    ή
    -0.06
    UCKET
    -0.06
     Morr
    -0.06
    pins
    -0.06
    bish
    -0.06
    oeff
    -0.05
    евиÑĩ
    -0.05
    POSITIVE LOGITS
     lá»±a
    0.07
    alers
    0.07
    ìŀ¥
    0.07
    .ul
    0.07
    ãĥĥãĥĹ
    0.07
    ugs
    0.07
     options
    0.07
    467
    0.06
     заÑģÑĤав
    0.06
     ÙħÙħ
    0.06
    Activations Density 0.021%

    No Known Activations