© 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. 39249
    Prev
    Next
    INDEX
    Explanations

    information related to microorganisms and their impact on health

    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
     antioxid
    -0.08
     reportedly
    -0.06
    phanumeric
    -0.06
     allegedly
    -0.06
    ilibrium
    -0.06
    ì°¸
    -0.06
     presup
    -0.06
     weather
    -0.06
    çĶ²
    -0.05
    hive
    -0.05
    POSITIVE LOGITS
     (~
    0.06
    kich
    0.06
     embar
    0.06
    ointed
    0.06
    anan
    0.06
    ĤŃ
    0.06
     VERY
    0.06
    nds
    0.06
     backwards
    0.06
     èĬ±
    0.06
    Activations Density 0.010%

    No Known Activations