© 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. 82316
    Prev
    Next
    INDEX
    Explanations

    references to historical events and treaties

    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
    /DD
    -0.07
    oader
    -0.07
    ailles
    -0.07
    usra
    -0.06
    ÃŃlia
    -0.06
    nyder
    -0.06
     Daly
    -0.06
     domest
    -0.06
    SWG
    -0.06
    auga
    -0.06
    POSITIVE LOGITS
     Ign
    0.07
     mapa
    0.07
    tvrt
    0.07
    ávÄĽ
    0.07
    çĵľ
    0.07
    ÑģÑĤеÑĢ
    0.06
     corrid
    0.06
    649
    0.06
    fi
    0.06
    erb
    0.06
    Activations Density 0.123%

    No Known Activations