© 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. 15547
    Prev
    Next
    INDEX
    Explanations

    concepts related to significance and relevance in discussions

    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
     trp
    -0.06
     compatible
    -0.06
     Wend
    -0.06
     comprehensive
    -0.06
    entic
    -0.06
    endors
    -0.06
    طبÙĬ
    -0.06
    лаÑĪ
    -0.05
    edio
    -0.05
    avanaugh
    -0.05
    POSITIVE LOGITS
     importance
    0.20
     Importance
    0.18
     significance
    0.17
    éĩįè¦ģ
    0.16
     relevance
    0.15
     important
    0.14
     importante
    0.14
    important
    0.14
     Important
    0.14
     ì¤ijìļĶ
    0.13
    Activations Density 0.049%

    No Known Activations