© 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. 60368
    Prev
    Next
    INDEX
    Explanations

    punctuation and structure within sentences

    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
    æ²¢
    -0.06
    _RENDERER
    -0.06
     PYTHON
    -0.06
     :↵↵
    -0.06
    :↵↵
    -0.06
    оги
    -0.06
     :↵
    -0.05
     ξεÏĦα
    -0.05
    :↵
    -0.05
    ظ
    -0.05
    POSITIVE LOGITS
     our
    0.11
     we
    0.10
    æĪij们çļĦ
    0.08
    æĪij们
    0.08
    our
    0.08
    æĪijåĢij
    0.08
     We
    0.08
     generally
    0.08
     наÑĪей
    0.07
     Our
    0.07
    Activations Density 0.007%

    No Known Activations