© 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. 78835
    Prev
    Next
    INDEX
    Explanations

    events and gatherings related to community and culture

    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
    ä½įæĸ¼
    -0.13
    ä½įäºİ
    -0.13
     located
    -0.12
    located
    -0.11
     location
    -0.11
    -location
    -0.10
     Located
    -0.10
     locations
    -0.10
    locations
    -0.10
    location
    -0.10
    POSITIVE LOGITS
     dort
    0.08
     surrounded
    0.06
     chancellor
    0.06
    .mk
    0.06
     Dort
    0.06
    andard
    0.06
    isel
    0.06
    bane
    0.06
     Organic
    0.06
     Visibility
    0.06
    Activations Density 0.116%

    No Known Activations