© 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. 59127
    Prev
    Next
    INDEX
    Explanations

    references to numerical values or quantifiable data

    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
    tin
    -0.06
    Overflow
    -0.06
     калÑĮ
    -0.06
     веÑī
    -0.06
    že
    -0.06
    glich
    -0.06
    NU
    -0.06
    gard
    -0.06
    pose
    -0.06
    semblies
    -0.06
    POSITIVE LOGITS
     fewer
    0.09
     whe
    0.08
    numberOf
    0.07
     wheels
    0.07
     syll
    0.07
     Wheeler
    0.07
     petals
    0.07
     wing
    0.07
     sal
    0.07
     numberOf
    0.07
    Activations Density 0.128%

    No Known Activations