© 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. 84948
    Prev
    Next
    INDEX
    Explanations

    terms related to car specifications and performance features

    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
    luž
    -0.09
    ivia
    -0.08
    ategorized
    -0.07
    oui
    -0.07
     ActionTypes
    -0.07
    ãģªãģĹ
    -0.07
    embros
    -0.07
    arsi
    -0.07
    oped
    -0.07
    erap
    -0.06
    POSITIVE LOGITS
    kowski
    0.07
    аÑĢÑħ
    0.07
    /single
    0.06
    tract
    0.06
    bor
    0.06
    apor
    0.06
     bor
    0.06
    /full
    0.06
    arden
    0.06
    borrow
    0.06
    Activations Density 0.004%

    No Known Activations