© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 93692
    Prev
    Next
    INDEX
    Explanations

    financial performance indicators and disclaimers related to investments

    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
    asel
    -0.07
    ems
    -0.06
    rys
    -0.06
     biz
    -0.06
     supporting
    -0.06
    uai
    -0.06
    ÙĪÙĨÙĩ
    -0.06
    ibles
    -0.06
    itbart
    -0.06
    ัà¸ķว
    -0.06
    POSITIVE LOGITS
     benchmarks
    0.07
    performance
    0.07
    tual
    0.07
    eriod
    0.07
    kazy
    0.07
     Vampire
    0.07
    phe
    0.06
     Performance
    0.06
     Paladin
    0.06
    aque
    0.06
    Activations Density 0.036%

    No Known Activations