© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90714
    Prev
    Next
    INDEX
    Explanations

    phrases related to repetition or recurrence of events

    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
    ILLA
    -0.07
    LLU
    -0.06
    æĮĻ
    -0.06
    _FALL
    -0.06
    ãģĶãģĸãģĦãģ¾ãģĻ
    -0.06
    PLEX
    -0.06
    ervlet
    -0.06
    該
    -0.06
    sequential
    -0.06
    illa
    -0.06
    POSITIVE LOGITS
     (++
    0.07
    tridge
    0.07
    jun
    0.06
     WCHAR
    0.06
    wen
    0.06
     meld
    0.06
    %%%%%%%%%%%%%%%%
    0.06
    ween
    0.06
    stup
    0.06
    (++
    0.06
    Activations Density 0.000%

    No Known Activations