© 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. 125532
    Prev
    Next
    INDEX
    Explanations

    actions involving stopping or starting movement

    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
     escal
    -0.07
     rail
    -0.07
    SGlobal
    -0.07
    rail
    -0.07
     Railway
    -0.07
    Rail
    -0.07
     stair
    -0.07
     Rail
    -0.07
     travellers
    -0.06
     trek
    -0.06
    POSITIVE LOGITS
     parking
    0.14
     driving
    0.13
     drive
    0.12
     Parking
    0.12
    Parking
    0.12
     drives
    0.11
     Drive
    0.11
    Drive
    0.11
     drove
    0.11
    drive
    0.10
    Activations Density 0.067%

    No Known Activations