© 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. 86382
    Prev
    Next
    INDEX
    Explanations

    references to sensors and detection mechanisms for harmful substances

    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
    AccessType
    -0.07
    ãĥł
    -0.06
     deg
    -0.06
    725
    -0.06
    istar
    -0.06
    ÑĤÑĮ
    -0.06
    761
    -0.06
    ostat
    -0.06
    ált
    -0.06
     Äijỡ
    -0.06
    POSITIVE LOGITS
     traces
    0.12
     trace
    0.11
     presence
    0.10
     detect
    0.10
     levels
    0.09
     detection
    0.09
    Detect
    0.09
     detections
    0.09
    _trace
    0.09
     detecting
    0.09
    Activations Density 0.055%

    No Known Activations