© 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. 39137
    Prev
    Next
    INDEX
    Explanations

    expressions indicating ease of acceptance or popularity

    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
    orda
    -0.07
    jack
    -0.07
    stell
    -0.06
    ums
    -0.06
     kia
    -0.06
     Eisen
    -0.06
    cta
    -0.06
    ±
    -0.06
     Alto
    -0.06
    jis
    -0.06
    POSITIVE LOGITS
    pour
    0.07
    ä¸ĭæĿ¥
    0.07
    oud
    0.07
    stanov
    0.07
    patrick
    0.07
    оÑĪ
    0.06
     Erot
    0.06
     down
    0.06
     undermin
    0.06
    ovnÃŃ
    0.06
    Activations Density 0.020%

    No Known Activations