© 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. 28151
    Prev
    Next
    INDEX
    Explanations

    terms related to combustible materials and fuels

    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
    844
    -0.06
     open
    -0.06
     convert
    -0.06
     struct
    -0.06
     circumstances
    -0.06
    á»Ĩ
    -0.06
     divert
    -0.06
    OST
    -0.06
     wid
    -0.05
     lips
    -0.05
    POSITIVE LOGITS
    ogenerated
    0.08
    krv
    0.08
    ÙĪÙħات
    0.08
    Ñħод
    0.08
     воздÑĥÑħ
    0.08
     пой
    0.08
     tÆ°Æ¡i
    0.08
    .SK
    0.07
     material
    0.07
     tane
    0.07
    Activations Density 0.085%

    No Known Activations