© 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. 15-LLAMASCOPE-RES-131K
    11. 87019
    Prev
    Next
    INDEX
    Explanations

    sections that involve identifiers and summaries in documentation

    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
    omic
    -0.08
    asto
    -0.06
    avin
    -0.06
    ixon
    -0.06
    emme
    -0.06
    lien
    -0.06
     jour
    -0.06
    rega
    -0.06
     Imper
    -0.06
    enna
    -0.06
    POSITIVE LOGITS
    è¶
    0.06
    ulfilled
    0.06
     Excell
    0.06
    odial
    0.06
    antes
    0.06
    rtl
    0.06
     fatt
    0.06
    dealloc
    0.06
    slaught
    0.06
     Beth
    0.06
    Activations Density 0.000%

    No Known Activations