© 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. 4808
    Prev
    Next
    INDEX
    Explanations

    alternative options or choices in various contexts

    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
    kle
    -0.08
    egan
    -0.07
    gers
    -0.07
    zej
    -0.07
    kara
    -0.07
     hereby
    -0.07
    achuset
    -0.06
    imon
    -0.06
    ayar
    -0.06
    нÑİ
    -0.06
    POSITIVE LOGITS
    angel
    0.07
    ignal
    0.07
     ladder
    0.06
    arrera
    0.06
    anje
    0.06
    .scalablytyped
    0.06
    leans
    0.06
    illis
    0.06
    phe
    0.06
     Gould
    0.06
    Activations Density 0.042%

    No Known Activations