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

    Neuronpedia

    Jacobian LensNEW
    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. 60993
    Prev
    Next
    INDEX
    Explanations

    structured information related to organizational or regulatory details

    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
     might
    -0.06
    eka
    -0.06
    ino
    -0.06
    T
    -0.06
     even
    -0.06
    ko
    -0.06
     rap
    -0.06
    ime
    -0.06
     finally
    -0.05
    able
    -0.05
    POSITIVE LOGITS
     therefore
    0.12
     hence
    0.09
     daher
    0.09
     Therefore
    0.09
    herits
    0.09
     donc
    0.08
     поÑįÑĤомÑĥ
    0.08
    Therefore
    0.08
    assi
    0.08
     consequently
    0.08
    Activations Density 0.033%

    No Known Activations