© 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. 77202
    Prev
    Next
    INDEX
    Explanations

    references to academic sources or citations

    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
    enci
    -0.08
     kontakt
    -0.07
    aber
    -0.07
    ewan
    -0.07
    woo
    -0.06
    orny
    -0.06
    å¼ķãģį
    -0.06
    rets
    -0.06
    icker
    -0.06
    uchen
    -0.06
    POSITIVE LOGITS
     ÑģобоÑİ
    0.06
    NECT
    0.06
    ATAB
    0.06
    citation
    0.06
    SCP
    0.06
    .hr
    0.06
     scaleY
    0.06
    íĿ¥
    0.06
     pent
    0.06
    PHY
    0.06
    Activations Density 0.004%

    No Known Activations