© 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. 15-LLAMASCOPE-RES-131K
    11. 89468
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and certain contextual references

    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
    acted
    -0.07
    ãģŁãĤī
    -0.06
    .CONTENT
    -0.06
     Kontakt
    -0.06
    ¢åįķ
    -0.06
    acting
    -0.06
     denom
    -0.06
    isle
    -0.06
    æı
    -0.06
    rama
    -0.06
    POSITIVE LOGITS
    arcy
    0.06
    omain
    0.06
    ities
    0.06
    agan
    0.06
    WSC
    0.06
    apon
    0.06
    eh
    0.06
    iant
    0.06
     Mog
    0.06
    anch
    0.05
    Activations Density 0.000%

    No Known Activations