© 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. 29232
    Prev
    Next
    INDEX
    Explanations

    references to scientific discussions and parameters related to energy and physics

    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
    à¹ĥ
    -0.07
    ÃĹ↵↵
    -0.07
    ordes
    -0.06
    ÌĪ
    -0.06
    UNG
    -0.06
    çĹ
    -0.06
    ört
    -0.06
     uch
    -0.06
     Maz
    -0.06
    quo
    -0.06
    POSITIVE LOGITS
     earlier
    0.17
     previously
    0.14
     Earlier
    0.13
     previous
    0.12
     Previously
    0.12
    Earlier
    0.12
     already
    0.12
    Previously
    0.12
    ear
    0.11
    previous
    0.10
    Activations Density 0.205%

    No Known Activations