© 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. 107448
    Prev
    Next
    INDEX
    Explanations

    fragments of text related to technical documentation or programming code

    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
    vas
    -0.06
     kontakte
    -0.06
    rip
    -0.06
    cession
    -0.06
     voks
    -0.06
    velte
    -0.06
    raman
    -0.06
     insp
    -0.06
     Commonwealth
    -0.06
    ại
    -0.06
    POSITIVE LOGITS
    orsi
    0.07
    .infinity
    0.07
    isper
    0.07
    .googleapis
    0.07
    (DialogInterface
    0.07
    bole
    0.06
    otti
    0.06
    uma
    0.06
    zbollah
    0.06
    ugs
    0.06
    Activations Density 0.006%

    No Known Activations