© 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. 15-LLAMASCOPE-RES-131K
    11. 62004
    Prev
    Next
    INDEX
    Explanations

    concepts related to success and the challenges of achieving it

    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
    _MAJOR
    -0.07
    signature
    -0.06
    DataTask
    -0.06
    rink
    -0.06
     bonded
    -0.06
    entar
    -0.06
    stro
    -0.06
    ptune
    -0.06
    èĬ
    -0.06
    straction
    -0.06
    POSITIVE LOGITS
    alth
    0.07
     plán
    0.07
     actively
    0.07
     Explicit
    0.07
     intentional
    0.07
     explicitly
    0.07
     Artificial
    0.07
     planned
    0.07
     deliberate
    0.07
     manual
    0.07
    Activations Density 0.077%

    No Known Activations