© 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. 81135
    Prev
    Next
    INDEX
    Explanations

    scientific terms and concepts related to gene expression and regulatory mechanisms

    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
     Worldwide
    -0.06
     Rosenberg
    -0.06
     millions
    -0.06
    åĨµ
    -0.06
     candidate
    -0.06
     spoiler
    -0.06
     Nes
    -0.06
     worldwide
    -0.06
     vocabulary
    -0.06
    :
    -0.05
    POSITIVE LOGITS
    çģ
    0.09
    ¦æĥħ
    0.08
    æĭŁ
    0.08
    Å¡ek
    0.08
    rupa
    0.07
    arkan
    0.07
    _CONTINUE
    0.07
    ixon
    0.07
    ,proto
    0.07
    CRET
    0.07
    Activations Density 0.043%

    No Known Activations