© 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. 27831
    Prev
    Next
    INDEX
    Explanations

    specific codes or identifiers related to modules or data structures

    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
    uhe
    -0.06
     provision
    -0.06
    yang
    -0.06
    ë¡
    -0.06
    kar
    -0.06
    .sk
    -0.06
    avanaugh
    -0.06
     Hers
    -0.06
     Prel
    -0.06
    alth
    -0.05
    POSITIVE LOGITS
    ozem
    0.08
    amat
    0.07
    CLU
    0.07
    ECTOR
    0.06
    ¥
    0.06
     ëĭ¹
    0.06
    -mount
    0.06
    enez
    0.06
    åIJ¯
    0.06
     Dol
    0.06
    Activations Density 0.033%

    No Known Activations