© 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. 5-LLAMASCOPE-RES-131K
    11. 126417
    Prev
    Next
    INDEX
    Explanations

    financial performance indicators and stock-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
    cci
    -0.06
    ÙĪرت
    -0.06
    cee
    -0.06
    prov
    -0.06
    mente
    -0.06
    hiro
    -0.06
     plano
    -0.06
    ulp
    -0.06
    ç
    -0.06
    ambi
    -0.06
    POSITIVE LOGITS
    YLE
    0.07
    oras
    0.07
    ToF
    0.06
    oney
    0.06
    ighting
    0.06
    γÏĮ
    0.06
    æ©ĭ
    0.06
     Chall
    0.06
    dns
    0.06
    िषय
    0.06
    Activations Density 0.003%

    No Known Activations