© 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. 54198
    Prev
    Next
    INDEX
    Explanations

    phrases related to the operation and safety within body shops

    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
    cke
    -0.07
    jedn
    -0.07
    angs
    -0.07
     struk
    -0.07
    £p
    -0.07
    ytt
    -0.07
    RAND
    -0.07
     cdr
    -0.07
    enic
    -0.06
    еÑĢÑĸг
    -0.06
    POSITIVE LOGITS
     dust
    0.07
     tempor
    0.07
     temporary
    0.07
     during
    0.07
    æľŁéĹ´
    0.06
    during
    0.06
    ¢åįķ
    0.06
     вÑĢем
    0.06
     displaced
    0.06
     Temporary
    0.06
    Activations Density 0.012%

    No Known Activations