© 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. 9-LLAMASCOPE-RES-131K
    11. 94780
    Prev
    Next
    INDEX
    Explanations

    terms related to file management and system commands

    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
    δει
    -0.07
    intval
    -0.06
    erville
    -0.06
    sey
    -0.06
    ,
    -0.05
     textbooks
    -0.05
    endon
    -0.05
     mean
    -0.05
    cribe
    -0.05
     fair
    -0.05
    POSITIVE LOGITS
    اÙĪÙĨد
    0.07
    YG
    0.07
    orro
    0.07
    _nh
    0.07
    æľ¬å½ĵ
    0.07
    utin
    0.07
    voje
    0.07
    ýš
    0.07
    ogan
    0.07
    imité
    0.06
    Activations Density 0.022%

    No Known Activations