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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 82700
    Prev
    Next
    INDEX
    Explanations

    code elements related to programming libraries and frameworks

    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
    993
    -0.07
    ogens
    -0.06
     Oz
    -0.06
    ieu
    -0.06
     Rams
    -0.06
     Bil
    -0.06
    trand
    -0.06
     欧
    -0.06
    dataProvider
    -0.06
    ambre
    -0.06
    POSITIVE LOGITS
    ÌĢ
    0.07
    oS
    0.07
    orum
    0.06
    Brief
    0.06
     trag
    0.06
    metro
    0.06
    BD
    0.06
    078
    0.06
    uring
    0.06
     Brief
    0.06
    Activations Density 0.000%

    No Known Activations