© 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. 125131
    Prev
    Next
    INDEX
    Explanations

    references to specific timeframes, particularly relating to years, months, weeks, and days

    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
     somehow
    -0.07
    v
    -0.06
    U
    -0.06
    opard
    -0.06
    VERBOSE
    -0.06
    esso
    -0.06
    at
    -0.06
    st
    -0.06
    V
    -0.06
    amp
    -0.06
    POSITIVE LOGITS
     dozen
    0.11
     málo
    0.08
     деÑģÑıÑĤ
    0.08
    åĿĽ
    0.08
    /stdc
    0.08
    ìĶ©
    0.07
     hundred
    0.07
     thousand
    0.07
     Hundred
    0.07
    -toggler
    0.07
    Activations Density 0.025%

    No Known Activations