© 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. 71086
    Prev
    Next
    INDEX
    Explanations

    numerical values and statistics related to performance metrics

    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
    azon
    -0.07
    eus
    -0.07
    oj
    -0.07
    æĹ¢
    -0.07
     بÙĪØ§Ø¨Ø©
    -0.07
    ัà¸Ĵ
    -0.07
    chor
    -0.07
    nesc
    -0.06
    oby
    -0.06
    olor
    -0.06
    POSITIVE LOGITS
     etc
    0.09
    etc
    0.06
     |
    0.06
     eoq
    0.06
    zar
    0.06
    isses
    0.06
     ÑĤоÑīо
    0.06
    \OptionsResolver
    0.06
     Gio
    0.06
    æĮº
    0.06
    Activations Density 0.038%

    No Known Activations