© 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. 56339
    Prev
    Next
    INDEX
    Explanations

    references to technological products or services

    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
    sth
    -0.07
    _tcb
    -0.07
    ERE
    -0.07
    ptrdiff
    -0.07
     opener
    -0.07
    ere
    -0.06
    otland
    -0.06
    /Foundation
    -0.06
    CriticalSection
    -0.06
    ↵↵
    -0.06
    POSITIVE LOGITS
     &
    0.06
    vect
    0.06
    kud
    0.06
    ONSE
    0.06
    AdapterManager
    0.06
     mastur
    0.06
    ÂĽ
    0.06
     Placement
    0.06
    azo
    0.06
     Offline
    0.06
    Activations Density 0.000%

    No Known Activations