© 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. 126798
    Prev
    Next
    INDEX
    Explanations

    references to points in time or source citations

    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
    tractor
    -0.07
    вÑĸÑĤ
    -0.07
    alon
    -0.07
    Directive
    -0.06
    alars
    -0.06
    ëı
    -0.06
    =end
    -0.06
    èĪĮ
    -0.06
    quo
    -0.06
    elerik
    -0.06
    POSITIVE LOGITS
    acci
    0.07
     célib
    0.06
    èĢĮ
    0.06
    ks
    0.06
     plais
    0.06
     naked
    0.05
     different
    0.05
    ģı
    0.05
     Different
    0.05
    krit
    0.05
    Activations Density 0.024%

    No Known Activations