© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 79005
    Prev
    Next
    INDEX
    Explanations

    mentions of content responsibility and accuracy in media and listings

    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
    dge
    -0.06
    rix
    -0.06
    ix
    -0.06
    ÅĻÃŃz
    -0.06
    aja
    -0.06
    atham
    -0.06
    iores
    -0.06
    utes
    -0.06
     Graves
    -0.06
    lique
    -0.06
    POSITIVE LOGITS
     nor
    0.09
    ÑĩаÑģÑĤ
    0.08
    accuracy
    0.08
    nor
    0.07
     anymore
    0.07
    iaux
    0.07
    onis
    0.07
     accuracy
    0.07
    akit
    0.07
    aucoup
    0.06
    Activations Density 0.003%

    No Known Activations