© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 105776
    Prev
    Next
    INDEX
    Explanations

    terms related to flux and density measurements in astrophysical contexts

    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
     pong
    -0.06
    iform
    -0.06
    ley
    -0.06
    á»Ļn
    -0.06
    ë£
    -0.06
    uc
    -0.06
    iversal
    -0.06
    оÑĩнÑĭй
    -0.06
    onomous
    -0.06
    bj
    -0.06
    POSITIVE LOGITS
    Animating
    0.07
    ROADCAST
    0.07
    entai
    0.07
    ruise
    0.07
    aston
    0.06
    Animate
    0.06
    èĪĮ
    0.06
    Animated
    0.06
     dece
    0.06
    orsi
    0.06
    Activations Density 0.147%

    No Known Activations