© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 74840
    Prev
    Next
    INDEX
    Explanations

    references to time, duration, and efficiency in various contexts

    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
    ÑĨеÑģ
    -0.06
    [frame
    -0.06
    mods
    -0.06
    teri
    -0.06
    pNet
    -0.06
     SPEED
    -0.06
    issen
    -0.06
    uali
    -0.06
    tone
    -0.06
    ìļ´ëį°
    -0.06
    POSITIVE LOGITS
    -term
    0.09
     dÃłi
    0.09
    -short
    0.08
     shortest
    0.08
    -lived
    0.08
     serialVersionUID
    0.08
     longest
    0.07
    -lasting
    0.07
     sentences
    0.07
    -duration
    0.07
    Activations Density 0.034%

    No Known Activations