© 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. 16300
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations

    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
    atoi
    -0.07
    azy
    -0.06
     reservoir
    -0.06
    ijken
    -0.06
     Motors
    -0.06
     wedge
    -0.06
     sor
    -0.06
    sworth
    -0.06
    ovsky
    -0.06
    undi
    -0.06
    POSITIVE LOGITS
     åıĮ
    0.08
    uby
    0.07
    360
    0.07
    åıĮ
    0.07
    akis
    0.07
    562
    0.07
     textStatus
    0.07
    ÑİÑĢ
    0.07
     dual
    0.07
    pread
    0.07
    Activations Density 0.156%

    No Known Activations