© 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. 94059
    Prev
    Next
    INDEX
    Explanations

    themes of collaborative efforts and community involvement in projects

    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
    ÙĬÙĨات
    -0.07
    åĭĩ
    -0.07
    zcze
    -0.07
    .Invariant
    -0.07
    Ø´ÙĪر
    -0.06
    ankind
    -0.06
    WithMany
    -0.06
     Jeg
    -0.06
    ç«ĭãģ¦
    -0.06
     uniform
    -0.06
    POSITIVE LOGITS
     project
    0.10
     Completion
    0.08
     completion
    0.08
    project
    0.07
     Work
    0.07
     Project
    0.07
     finished
    0.07
    czy
    0.07
     finish
    0.07
    enie
    0.07
    Activations Density 0.039%

    No Known Activations