© 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. 84982
    Prev
    Next
    INDEX
    Explanations

    instructions related to organization and management tasks

    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
    gif
    -0.07
    ullo
    -0.07
    ermann
    -0.06
    rawtypes
    -0.06
     Lynch
    -0.06
    anki
    -0.06
    lef
    -0.06
    ozem
    -0.06
     nên
    -0.06
    inson
    -0.06
    POSITIVE LOGITS
    åIJ§
    0.08
     nhé
    0.07
    åį
    0.07
    RATE
    0.07
    PPER
    0.07
    ypi
    0.07
    avage
    0.06
    esteem
    0.06
    -MM
    0.06
     Miy
    0.06
    Activations Density 0.017%

    No Known Activations