© 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. 62657
    Prev
    Next
    INDEX
    Explanations

    references to miscellaneous or additional items or categories

    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
     ones
    -0.08
    kaz
    -0.07
    .Names
    -0.07
    erea
    -0.07
    koli
    -0.06
    Matchers
    -0.06
    blr
    -0.06
    еÑı
    -0.06
     lÆ°Æ¡ng
    -0.06
    ea
    -0.06
    POSITIVE LOGITS
     Bom
    0.07
    esser
    0.07
     alike
    0.07
    alice
    0.07
    igner
    0.07
    iner
    0.06
    inge
    0.06
     Guth
    0.06
    imir
    0.06
    890
    0.06
    Activations Density 0.020%

    No Known Activations