© 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. 15-LLAMASCOPE-RES-131K
    11. 445
    Prev
    Next
    INDEX
    Explanations

    attributes and features related to vehicles, particularly in an automotive context

    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
    ropol
    -0.10
    otime
    -0.07
    burger
    -0.07
    subst
    -0.07
     Bened
    -0.07
    æ··
    -0.07
    Resizable
    -0.07
    erif
    -0.06
    rome
    -0.06
    iens
    -0.06
    POSITIVE LOGITS
     front
    0.06
     mud
    0.06
     Wet
    0.06
     cross
    0.06
     wet
    0.06
     Spray
    0.06
     Lud
    0.06
    638
    0.06
     Cross
    0.06
     Wire
    0.06
    Activations Density 0.029%

    No Known Activations