© 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. 54891
    Prev
    Next
    INDEX
    Explanations

    references to the retrieval and return of lost or stolen items

    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
    /pdf
    -0.07
    ضÙĬ
    -0.06
    hausen
    -0.06
     onBind
    -0.06
    $log
    -0.06
    zell
    -0.06
    clc
    -0.06
    ÙĪتÛĮ
    -0.06
    .getRuntime
    -0.06
    rats
    -0.06
    POSITIVE LOGITS
     return
    0.13
    -return
    0.12
     returned
    0.12
    æĪ»
    0.12
     recovered
    0.11
    return
    0.11
     reclaim
    0.11
     returning
    0.11
     recovery
    0.10
     Return
    0.10
    Activations Density 0.081%

    No Known Activations