© 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. 72337
    Prev
    Next
    INDEX
    Explanations

    terms related to reconstruction and reordering

    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
    ãĤ¶
    -0.07
    imetype
    -0.07
    ader
    -0.07
    angent
    -0.07
     repeated
    -0.07
    ouz
    -0.07
     Sentry
    -0.07
     repeat
    -0.06
    ereal
    -0.06
    cation
    -0.06
    POSITIVE LOGITS
    naissance
    0.10
    orative
    0.07
    itories
    0.07
    eds
    0.07
    stakes
    0.06
    ponsible
    0.06
    ette
    0.06
    ator
    0.06
    ettes
    0.06
    /update
    0.06
    Activations Density 0.093%

    No Known Activations