© 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. 126396
    Prev
    Next
    INDEX
    Explanations

    indicators of financial or organizational structures

    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
    ompiler
    -0.08
     Ago
    -0.08
    reator
    -0.08
     ç·
    -0.08
    ηγ
    -0.07
    osate
    -0.07
    errals
    -0.07
    oman
    -0.07
    ÄĻd
    -0.07
     íĴĢ
    -0.07
    POSITIVE LOGITS
     most
    0.07
    il
    0.07
    andi
    0.06
     tie
    0.06
     latter
    0.06
    eed
    0.06
    uish
    0.06
     tuning
    0.06
    anny
    0.06
    _PUR
    0.06
    Activations Density 0.036%

    No Known Activations