© 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. 126398
    Prev
    Next
    INDEX
    Explanations

    articles and determiners indicative of specific subjects or issues

    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
    éŁ¿
    -0.08
    ovel
    -0.08
     ÙħÙĨظ
    -0.08
    çĬ
    -0.07
    isposable
    -0.07
    ynchronously
    -0.07
    ноÑĪ
    -0.07
    ansi
    -0.07
     cá»ij
    -0.07
    ноп
    -0.07
    POSITIVE LOGITS
     recent
    0.14
     recently
    0.11
    recent
    0.10
     earlier
    0.10
     previous
    0.08
     trend
    0.08
     Recent
    0.08
    Recent
    0.07
    inness
    0.07
     Trend
    0.07
    Activations Density 0.045%

    No Known Activations