© 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. 56122
    Prev
    Next
    INDEX
    Explanations

    terms related to electric vehicle infrastructure and services

    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
     Junk
    -0.07
    егод
    -0.06
     continuum
    -0.06
    pak
    -0.06
    ISCO
    -0.06
     Vegas
    -0.06
     flight
    -0.06
    ανά
    -0.05
    Ware
    -0.05
    lap
    -0.05
    POSITIVE LOGITS
     charging
    0.11
     Charging
    0.10
    charging
    0.09
     electric
    0.08
     charg
    0.08
     charger
    0.08
     charge
    0.07
    åħħ
    0.07
     Charge
    0.07
    rella
    0.07
    Activations Density 0.003%

    No Known Activations