© 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. 9-LLAMASCOPE-RES-131K
    11. 96387
    Prev
    Next
    INDEX
    Explanations

    terms related to fleet management and vehicles

    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
    ihan
    -0.08
    øy
    -0.07
    otta
    -0.07
    ÏĨι
    -0.07
     Svens
    -0.07
     disg
    -0.06
    iffe
    -0.06
    oÅĻ
    -0.06
     Dün
    -0.06
    itus
    -0.06
    POSITIVE LOGITS
     Quarry
    0.06
    bp
    0.06
     Oval
    0.06
    atu
    0.06
     Arbor
    0.06
    /fw
    0.06
    er
    0.06
     bushes
    0.06
    erc
    0.06
    _REPLACE
    0.06
    Activations Density 0.012%

    No Known Activations