© 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. 119312
    Prev
    Next
    INDEX
    Explanations

    details about electric vehicle specifications and 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
    phem
    -0.07
    ãĥ³ãĥĨãĤ£
    -0.07
     hik
    -0.07
    setw
    -0.07
    åĽ£
    -0.07
    rak
    -0.06
    istrovstvÃŃ
    -0.06
    agged
    -0.06
    quipment
    -0.06
    _intr
    -0.06
    POSITIVE LOGITS
    urray
    0.07
     Assist
    0.07
     Hybrid
    0.07
    furt
    0.07
     power
    0.07
     hybrid
    0.07
     battery
    0.06
     Solic
    0.06
     rear
    0.06
     brush
    0.06
    Activations Density 0.008%

    No Known Activations