© 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 EvalsExportsAPI 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. 57176
    Prev
    Next
    INDEX
    Explanations

    references to hidden or obscured items or locations

    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
    geb
    -0.07
    ãĥªãĤ«
    -0.07
    andon
    -0.07
    ÐŁÐļ
    -0.07
    ure
    -0.07
    ubo
    -0.07
    ÏĦοÏĤ
    -0.06
     treff
    -0.06
    $rs
    -0.06
    ãĤīãģĦ
    -0.06
    POSITIVE LOGITS
    neath
    0.08
    /out
    0.06
     Barcl
    0.06
     vide
    0.06
    etus
    0.06
    apps
    0.06
     guise
    0.06
     RECEIVE
    0.06
    inal
    0.05
     Gomez
    0.05
    Activations Density 0.012%

    No Known Activations