© 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. 119282
    Prev
    Next
    INDEX
    Explanations

    words related to company and provider entities in various industries

    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
    czy
    -0.08
    itler
    -0.07
    ambre
    -0.07
    cx
    -0.07
     Hun
    -0.07
    धर
    -0.07
    olean
    -0.07
    acus
    -0.06
     Loren
    -0.06
    Gratis
    -0.06
    POSITIVE LOGITS
    Ñģко
    0.06
     vin
    0.06
     ç·
    0.06
     Rooney
    0.06
    isi
    0.06
    zi
    0.05
    ît
    0.05
    ena
    0.05
    475
    0.05
    _GAP
    0.05
    Activations Density 0.004%

    No Known Activations