© 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. 79020
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation marks in the text

    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
     although
    -0.08
    尽管
    -0.07
    опÑĢи
    -0.07
     Although
    -0.07
    è±Ĭ
    -0.07
    although
    -0.06
    anca
    -0.06
    ocks
    -0.06
    ãĥ¼ãĥĢ
    -0.06
    ÃŃrk
    -0.06
    POSITIVE LOGITS
     but
    0.10
     maar
    0.09
    but
    0.09
     αλλά
    0.07
     но
    0.07
    WindowState
    0.07
     nhÆ°ng
    0.07
     pero
    0.07
    iddi
    0.07
    duc
    0.07
    Activations Density 0.042%

    No Known Activations