© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 16182
    Prev
    Next
    INDEX
    Explanations

    phrases related to effectiveness 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
     sharp
    -0.07
    sharp
    -0.07
     Bain
    -0.06
     konk
    -0.06
    ippo
    -0.06
    abay
    -0.06
    ceed
    -0.06
    elta
    -0.06
     cca
    -0.06
    issen
    -0.06
    POSITIVE LOGITS
     fewer
    0.11
     more
    0.09
    æĽ´
    0.09
    ARGER
    0.09
    æĽ´å¤ļ
    0.09
     æĽ´
    0.08
     overall
    0.08
    overall
    0.08
    more
    0.08
     MORE
    0.08
    Activations Density 0.200%

    No Known Activations