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

    Neuronpedia

    Jacobian LensNEW
    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. 59278
    Prev
    Next
    INDEX
    Explanations

    specific formatting or syntactical structures within code or data snippets

    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
    burgh
    -0.07
    ener
    -0.06
    god
    -0.06
    ocha
    -0.06
    ноÑģ
    -0.06
    moduleId
    -0.06
    trie
    -0.06
    IGO
    -0.06
    Ñĩен
    -0.06
    chet
    -0.06
    POSITIVE LOGITS
     Third
    0.11
     Both
    0.11
     both
    0.11
     third
    0.10
    both
    0.10
     BOTH
    0.10
    Third
    0.10
    Both
    0.09
     обо
    0.09
     thirds
    0.09
    Activations Density 0.173%

    No Known Activations