© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27375
    Prev
    Next
    INDEX
    Explanations

    specific numerical references and their relations within the context

    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
    /REC
    -0.08
    lobs
    -0.07
    *out
    -0.07
     ÑģÑĤак
    -0.07
    adius
    -0.07
    ovah
    -0.07
    639
    -0.06
     actionTypes
    -0.06
    ustum
    -0.06
    dzi
    -0.06
    POSITIVE LOGITS
     lengths
    0.08
     lane
    0.08
     segments
    0.08
     Äijoạn
    0.08
    è·¯
    0.08
     path
    0.08
    -path
    0.08
     segment
    0.07
    path
    0.07
     route
    0.07
    Activations Density 0.084%

    No Known Activations