© 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. 16371
    Prev
    Next
    INDEX
    Explanations

    references to official documentation or certifications related to travel

    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
    tings
    -0.08
    ayar
    -0.07
    -mf
    -0.07
    mrt
    -0.06
    гаÑĢ
    -0.06
    г
    -0.06
    ëŀįëĭĪëĭ¤
    -0.06
    ragen
    -0.06
    elen
    -0.06
    ire
    -0.06
    POSITIVE LOGITS
     Gor
    0.07
     Neck
    0.07
    orton
    0.06
    dera
    0.06
     gor
    0.06
    ocz
    0.06
     каÑģ
    0.06
    nty
    0.06
     Mein
    0.06
    aney
    0.06
    Activations Density 0.002%

    No Known Activations