© 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. 15453
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations, particularly those related to organizations and institutions

    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
    idot
    -0.08
    ambique
    -0.07
    ffi
    -0.07
    ationship
    -0.07
    opers
    -0.07
    PTS
    -0.07
    antly
    -0.06
    nox
    -0.06
    ãģ°ãģĭãĤĬ
    -0.06
    ÙĪاÙĨ
    -0.06
    POSITIVE LOGITS
    edin
    0.07
    tol
    0.06
    fold
    0.06
    iones
    0.06
    ãĥ³ãĥĨãĤ£
    0.06
    allas
    0.06
    زب
    0.06
    odore
    0.06
    ted
    0.06
    OF
    0.06
    Activations Density 0.065%

    No Known Activations