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

    Neuronpedia

    Jacobian LensNEW
    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. 87551
    Prev
    Next
    INDEX
    Explanations

    definitions and descriptions of concepts or terms

    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
    oren
    -0.06
    _canvas
    -0.06
    irit
    -0.06
    ListOf
    -0.06
    RING
    -0.06
    ÙĤات
    -0.06
    ÙĦا
    -0.06
    овеÑĢ
    -0.06
    hatt
    -0.06
    ä¸ĬäºĨ
    -0.06
    POSITIVE LOGITS
    etto
    0.07
    ØŃÙħ
    0.06
    fx
    0.06
     definition
    0.06
    aci
    0.06
    ippers
    0.06
    _definition
    0.06
    definition
    0.06
    purpose
    0.06
    /classes
    0.06
    Activations Density 0.039%

    No Known Activations