© 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 EvalsExportsinterp-engineNEWAPI 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. 117641
    Prev
    Next
    INDEX
    Explanations

    terms related to accessibility and movement in transportation contexts

    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
    èĻķ
    -0.07
    ilton
    -0.07
    å¤Ħ
    -0.07
    azzi
    -0.07
    TypeInfo
    -0.07
    unsafe
    -0.07
    adiator
    -0.06
    istrovstvÃŃ
    -0.06
    iÅ¡tÄĽ
    -0.06
    ilities
    -0.06
    POSITIVE LOGITS
    iken
    0.06
     passing
    0.06
     heavy
    0.06
    ina
    0.06
    GMT
    0.06
    me
    0.06
    inc
    0.06
    vis
    0.06
     movement
    0.06
     bulky
    0.06
    Activations Density 0.024%

    No Known Activations