© 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. 17-LLAMASCOPE-RES-131K
    11. 59608
    Prev
    Next
    INDEX
    Explanations

    linguistic concepts and relationships, particularly those involving semantics and grammatical structures

    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
    ãĤĮãģ©
    -0.08
    obsolete
    -0.07
    Wake
    -0.07
    assel
    -0.07
    tones
    -0.07
    hra
    -0.07
     Wake
    -0.07
     Brace
    -0.06
    oldur
    -0.06
    åĨµ
    -0.06
    POSITIVE LOGITS
     learning
    0.07
     knowledge
    0.06
     Experiment
    0.06
     ë°°ìļ°
    0.06
     Chunk
    0.06
     Experimental
    0.06
     Orn
    0.06
    aji
    0.06
    ona
    0.06
     informat
    0.06
    Activations Density 0.001%

    No Known Activations