© 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. 55076
    Prev
    Next
    INDEX
    Explanations

    terms related to spelling and orthography

    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
    chner
    -0.07
    ppo
    -0.07
    lec
    -0.07
    ure
    -0.06
    nici
    -0.06
     Builders
    -0.06
    izr
    -0.06
    plete
    -0.06
    ICC
    -0.06
    erva
    -0.06
    POSITIVE LOGITS
    -checked
    0.07
    /sp
    0.07
    æı®
    0.06
    checker
    0.06
    uess
    0.06
    ARRY
    0.06
    TOTYPE
    0.06
    _runtime
    0.06
    $route
    0.06
    ãģĵãģĿ
    0.06
    Activations Density 0.004%

    No Known Activations