© 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. 107455
    Prev
    Next
    INDEX
    Explanations

    references to the dietary habits and behaviors of mosquitoes and related insects

    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
    azen
    -0.07
    rif
    -0.07
     retention
    -0.06
     ØŃØ°
    -0.06
    ätze
    -0.06
     stretch
    -0.06
    èħ¹
    -0.06
    owski
    -0.06
    356
    -0.06
     Tal
    -0.06
    POSITIVE LOGITS
    FRING
    0.08
    -INF
    0.07
    istine
    0.07
    amba
    0.06
    umin
    0.06
    anic
    0.06
    URING
    0.06
     å¾ĴæŃ©
    0.06
    ologne
    0.06
    ascar
    0.06
    Activations Density 0.014%

    No Known Activations