© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 58912
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods and single quotation marks, reflecting the structure and flow of sentences

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ãģįãģŁ
    -0.09
    STR
    -0.08
    à¹īà¸ĩ
    -0.07
    ülen
    -0.07
    ago
    -0.07
    иÑħ
    -0.06
    QL
    -0.06
    ร
    -0.06
    /or
    -0.06
    รส
    -0.06
    POSITIVE LOGITS
    ÂĿ
    0.17
    s
    0.13
    ed
    0.10
    nbsp
    0.10
    atan
    0.07
    ť
    0.07
    -'
    0.07
    ska
    0.07
    fra
    0.07
    -"
    0.07
    Activations Density 0.104%

    No Known Activations