© 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. 86012
    Prev
    Next
    INDEX
    Explanations

    actions and descriptions related to parking situations

    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
    /filter
    -0.07
    éªij
    -0.07
    ertext
    -0.07
    ï½į
    -0.07
    vsp
    -0.07
    _Static
    -0.07
    ivery
    -0.07
    urname
    -0.06
     destruct
    -0.06
    icontrol
    -0.06
    POSITIVE LOGITS
     parking
    0.10
     Parking
    0.09
     front
    0.08
    ior
    0.07
     rear
    0.07
    Parking
    0.07
    front
    0.07
     Front
    0.06
     shopping
    0.06
     Shopping
    0.06
    Activations Density 0.003%

    No Known Activations