© 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. 78386
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to software and coding

    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
    ÑĪиÑĢ
    -0.07
     kanal
    -0.07
    .Selenium
    -0.06
    blr
    -0.06
    iddi
    -0.06
    agens
    -0.06
    odnÃŃ
    -0.06
    Cancelled
    -0.06
    anim
    -0.06
    кан
    -0.06
    POSITIVE LOGITS
     limited
    0.10
     limitation
    0.10
    limited
    0.10
     Limited
    0.09
     LIMIT
    0.09
     limitations
    0.09
     Limit
    0.08
    limitations
    0.08
    .limit
    0.08
    Limited
    0.08
    Activations Density 0.009%

    No Known Activations