© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 89441
    Prev
    Next
    INDEX
    Explanations

    references to wildlife interactions and potential hazards

    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
    689
    -0.07
    ³
    -0.07
    liqu
    -0.06
    εÏį
    -0.06
    achie
    -0.06
    HEME
    -0.06
    ế
    -0.06
    amo
    -0.06
    IEL
    -0.06
    amble
    -0.06
    POSITIVE LOGITS
     symp
    0.07
    FFFFFFFF
    0.06
     nuisance
    0.06
    .paths
    0.06
    isu
    0.06
    TS
    0.06
    CAA
    0.06
     Alarm
    0.06
    /browser
    0.06
     mess
    0.05
    Activations Density 0.011%

    No Known Activations