© 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. 74771
    Prev
    Next
    INDEX
    Explanations

    scientific and mathematical expressions or variables

    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
    adge
    -0.08
    mother
    -0.07
    .Dto
    -0.07
     dovol
    -0.07
    ament
    -0.06
    imat
    -0.06
    OMATIC
    -0.06
    ymm
    -0.06
    exas
    -0.06
     conductivity
    -0.06
    POSITIVE LOGITS
     sinus
    0.07
    ango
    0.06
    FileManager
    0.06
    abox
    0.05
     winter
    0.05
    âng
    0.05
     isolation
    0.05
     Lif
    0.05
    caf
    0.05
    -muted
    0.05
    Activations Density 0.005%

    No Known Activations