© 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. 3825
    Prev
    Next
    INDEX
    Explanations

    discussions about dividends and financial metrics related to shares

    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
    intree
    -0.07
    anian
    -0.07
    unte
    -0.07
    atures
    -0.06
    кеÑĤ
    -0.06
    rega
    -0.06
    efa
    -0.06
    yr
    -0.06
     poz
    -0.06
    undle
    -0.06
    POSITIVE LOGITS
    رب
    0.06
     Contin
    0.06
     scheduled
    0.06
    èĬĿ
    0.06
    ident
    0.06
     harmless
    0.06
    AGAIN
    0.06
    esign
    0.06
     Zw
    0.06
    ãĤ¤ãĤº
    0.06
    Activations Density 0.001%

    No Known Activations