© 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. 58045
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods and question marks

    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
    etter
    -0.06
    agle
    -0.06
    aleb
    -0.06
    cent
    -0.06
    иÑĤов
    -0.06
    Å¡ak
    -0.06
     foss
    -0.06
    cip
    -0.06
    CENT
    -0.06
    ovich
    -0.06
    POSITIVE LOGITS
    amacare
    0.06
    684
    0.06
    ãĥ¶
    0.06
    XMLElement
    0.06
    samp
    0.06
    ModelIndex
    0.06
    åºŃ
    0.06
    Fab
    0.06
    ç¬
    0.06
     ÑĢай
    0.06
    Activations Density 0.001%

    No Known Activations