© 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. 71287
    Prev
    Next
    INDEX
    Explanations

    references to various forms of wildlife crime and conservation issues

    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
    meteor
    -0.06
     genu
    -0.06
     Cow
    -0.06
     sokak
    -0.06
    gas
    -0.06
     gyr
    -0.06
    pid
    -0.06
    REATED
    -0.06
    bsd
    -0.06
    ãĥ¡ãĥ³ãĥĪ
    -0.06
    POSITIVE LOGITS
     Protected
    0.08
    abwe
    0.07
     Wildlife
    0.07
     Rangers
    0.07
     ivory
    0.07
     wildlife
    0.07
    erman
    0.06
    ằm
    0.06
     game
    0.06
     Rolex
    0.06
    Activations Density 0.006%

    No Known Activations