© 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. 121006
    Prev
    Next
    INDEX
    Explanations

    references to environmental issues and firefighting

    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
     Swords
    -0.08
    gas
    -0.07
    ichen
    -0.07
    enn
    -0.07
    reeze
    -0.07
    .navigateByUrl
    -0.07
    plor
    -0.06
     Lauderdale
    -0.06
    txt
    -0.06
     Tide
    -0.06
    POSITIVE LOGITS
     fire
    0.10
     firefight
    0.10
     firefighters
    0.09
     fires
    0.09
     Fire
    0.08
    .fire
    0.08
     firefighter
    0.08
    çģ«
    0.08
     Fires
    0.07
    Fire
    0.07
    Activations Density 0.021%

    No Known Activations