© 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. 92178
    Prev
    Next
    INDEX
    Explanations

    terms related to web development 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
    igram
    -0.07
    andom
    -0.06
    fn
    -0.06
    es
    -0.06
    iel
    -0.06
     bande
    -0.06
    orgot
    -0.06
    ech
    -0.06
    igrams
    -0.06
    letcher
    -0.06
    POSITIVE LOGITS
    conde
    0.08
    (åľŁ
    0.07
     ydk
    0.07
    ÐĽÐŀ
    0.07
    iveau
    0.07
    oton
    0.07
    pawn
    0.07
    omanip
    0.07
    Âİ
    0.07
    رØŃ
    0.07
    Activations Density 0.001%

    No Known Activations