© 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. 27536
    Prev
    Next
    INDEX
    Explanations

    elements of a timeline or date

    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
    .PropertyType
    -0.06
    vm
    -0.06
     forg
    -0.06
    orta
    -0.06
     SERIES
    -0.06
    reat
    -0.06
    series
    -0.05
    rière
    -0.05
     ins
    -0.05
     Chambers
    -0.05
    POSITIVE LOGITS
    uluk
    0.08
    roker
    0.07
    ullet
    0.07
    ycz
    0.07
    eping
    0.06
    utory
    0.06
    ervas
    0.06
    #End
    0.06
    ulen
    0.06
    isor
    0.06
    Activations Density 0.006%

    No Known Activations