© 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. 104537
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to guidelines, standards, or recommended actions

    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
    ourn
    -0.07
    ifar
    -0.06
    rell
    -0.06
    serie
    -0.06
     mạch
    -0.06
    inis
    -0.06
    à¥ĩश
    -0.06
    rone
    -0.06
    uo
    -0.06
    ĺìĿ´
    -0.06
    POSITIVE LOGITS
     contained
    0.07
    تÙĬÙĨ
    0.06
     of
    0.06
    .resources
    0.06
     Kem
    0.06
    ASSES
    0.06
    ãģĴ
    0.06
    IRE
    0.06
    ienes
    0.06
     Font
    0.06
    Activations Density 0.061%

    No Known Activations