© 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. 55697
    Prev
    Next
    INDEX
    Explanations

    issues related to health, safety, and environmental impacts

    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
    ĥn
    -0.08
    ebin
    -0.07
     hopefully
    -0.07
     ÑģÑĩиÑĤаеÑĤÑģÑı
    -0.07
    Ymd
    -0.07
    è¨Ģãģ£ãģ¦
    -0.07
     ìķĮ볤
    -0.07
     reportedly
    -0.07
    zem
    -0.07
    .must
    -0.07
    POSITIVE LOGITS
     indeed
    0.10
     actually
    0.08
     Indeed
    0.07
     Actually
    0.07
    inde
    0.07
     zwar
    0.06
    .Toolkit
    0.06
    0.06
     contrary
    0.06
    actually
    0.06
    Activations Density 0.079%

    No Known Activations