© 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. 118798
    Prev
    Next
    INDEX
    Explanations

    mentions of companies and organizations related to various sectors and client types

    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
    å¥ī
    -0.08
    afort
    -0.08
    kul
    -0.07
    ĥĿ
    -0.07
    cak
    -0.07
    á»įng
    -0.07
    erto
    -0.07
    eko
    -0.07
    à¹Ĭà¸ģ
    -0.06
    eview
    -0.06
    POSITIVE LOGITS
     worldwide
    0.07
     across
    0.07
     alike
    0.07
     demands
    0.07
     Needs
    0.06
     needs
    0.06
    illery
    0.06
     Requirements
    0.06
    'gc
    0.06
    374
    0.06
    Activations Density 0.024%

    No Known Activations