© 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. 92508
    Prev
    Next
    INDEX
    Explanations

    descriptions of interior space and comfort in vehicles

    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
    eka
    -0.06
    -0.06
     span
    -0.06
    /run
    -0.06
    essed
    -0.06
    -run
    -0.05
     chain
    -0.05
    umbo
    -0.05
    ws
    -0.05
     outdoor
    -0.05
    POSITIVE LOGITS
     interior
    0.13
     interiors
    0.12
    Interior
    0.12
     inside
    0.11
    _inside
    0.11
    Inside
    0.11
    inside
    0.10
     Interior
    0.10
     Inside
    0.10
    åħ§
    0.10
    Activations Density 0.018%

    No Known Activations