© 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. 107634
    Prev
    Next
    INDEX
    Explanations

    features related to vehicle design and specifications

    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
     eyeb
    -0.08
     bò
    -0.07
     cân
    -0.07
     assort
    -0.07
    lobber
    -0.07
    resco
    -0.07
     privile
    -0.07
    $header
    -0.07
    iversal
    -0.07
     åīį
    -0.07
    POSITIVE LOGITS
     rear
    0.14
     tail
    0.13
     posterior
    0.12
     Rear
    0.12
    _tail
    0.11
    å°¾
    0.11
     backend
    0.10
     Tail
    0.10
    tail
    0.10
     behind
    0.10
    Activations Density 0.020%

    No Known Activations