© 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. 81676
    Prev
    Next
    INDEX
    Explanations

    references to authors and their published works

    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
    ÅĤaw
    -0.07
    zeich
    -0.07
    apter
    -0.07
     cref
    -0.07
    òn
    -0.07
    hausen
    -0.06
    лаÑģ
    -0.06
    ditor
    -0.06
    aise
    -0.06
     Passive
    -0.06
    POSITIVE LOGITS
     novels
    0.07
     informat
    0.07
     Releases
    0.07
     releases
    0.06
    EGA
    0.06
    843
    0.06
     nov
    0.06
    nov
    0.06
    rove
    0.06
    üven
    0.06
    Activations Density 0.021%

    No Known Activations