© 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. 74267
    Prev
    Next
    INDEX
    Explanations

    transportation-related details, including directions and routes

    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
    ÙıÙĪا
    -0.06
    ennon
    -0.06
    äºĭæĥħ
    -0.06
     Tall
    -0.06
    iloc
    -0.06
    evity
    -0.05
    ίοÏĤ
    -0.05
     DAT
    -0.05
    æŁ±
    -0.05
    wan
    -0.05
    POSITIVE LOGITS
    contin
    0.08
    orr
    0.07
     Contin
    0.07
    ahren
    0.07
    سÙĬ
    0.06
    ungan
    0.06
     Spor
    0.06
     Bren
    0.06
    Traversal
    0.06
     continu
    0.06
    Activations Density 0.001%

    No Known Activations