© 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. 82966
    Prev
    Next
    INDEX
    Explanations

    instances of numeric or percentage data related to companies

    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
    ocol
    -0.07
     ><?
    -0.07
    oog
    -0.07
    kara
    -0.07
    istik
    -0.07
    LIMIT
    -0.06
    ź
    -0.06
    arra
    -0.06
    IB
    -0.06
     å¹
    -0.06
    POSITIVE LOGITS
    appable
    0.07
    846
    0.06
     jenter
    0.06
    ảy
    0.06
     ranks
    0.06
     æŀĹ
    0.06
    _remain
    0.06
    μο
    0.06
    754
    0.06
    getVar
    0.05
    Activations Density 0.000%

    No Known Activations