© 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. 76374
    Prev
    Next
    INDEX
    Explanations

    elements related to law enforcement and crime scenes

    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
    _VC
    -0.07
    _NR
    -0.07
    icast
    -0.06
    ç¥ĸ
    -0.06
    åĪ«
    -0.06
    Endian
    -0.06
    atron
    -0.06
    undler
    -0.06
    íĶ½
    -0.06
    pio
    -0.06
    POSITIVE LOGITS
     exact
    0.08
     site
    0.08
     location
    0.08
    Exact
    0.07
     SITE
    0.07
     precise
    0.07
     spot
    0.07
    /site
    0.07
     footprint
    0.07
    amd
    0.06
    Activations Density 0.020%

    No Known Activations