© 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. 84701
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas and periods

    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
    lett
    -0.07
    rob
    -0.06
    /or
    -0.06
    à¥įरà¤ļ
    -0.06
    oom
    -0.06
    optera
    -0.06
    oki
    -0.06
    etic
    -0.06
    erv
    -0.06
    xima
    -0.06
    POSITIVE LOGITS
    s
    0.15
    ÂĿ
    0.11
    sak
    0.10
    Ùĩ
    0.08
    ment
    0.08
    hound
    0.08
    VERRIDE
    0.07
    ãģĤãģ£ãģŁ
    0.07
    ftware
    0.07
    ÏĤ
    0.07
    Activations Density 0.144%

    No Known Activations