© 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. 57034
    Prev
    Next
    INDEX
    Explanations

    specific types of games and event-related information

    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
    construct
    -0.06
    ajes
    -0.06
    659
    -0.06
    à¥Ģà¤Ĩà¤Ī
    -0.06
     Lars
    -0.06
    itur
    -0.06
    848
    -0.06
    ijing
    -0.05
    664
    -0.05
    449
    -0.05
    POSITIVE LOGITS
    ©
    0.07
    edl
    0.07
    hv
    0.07
     watch
    0.07
    /watch
    0.07
    Daemon
    0.07
    HQ
    0.07
    -watch
    0.06
    _watch
    0.06
    Bookmark
    0.06
    Activations Density 0.001%

    No Known Activations