© 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. 87063
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the absence of something or the presence of errors

    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
     cons
    -0.06
     aw
    -0.06
    溪
    -0.06
     Pes
    -0.06
     Bur
    -0.06
     fact
    -0.05
     Aw
    -0.05
     situ
    -0.05
    -alist
    -0.05
    ann
    -0.05
    POSITIVE LOGITS
    FOUND
    0.08
    ebra
    0.07
     Verfügung
    0.07
    /loose
    0.07
     disponible
    0.07
    altern
    0.07
    isy
    0.07
    found
    0.07
    ustum
    0.07
    zÄĻ
    0.07
    Activations Density 0.019%

    No Known Activations