© 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. 5-LLAMASCOPE-RES-131K
    11. 126678
    Prev
    Next
    INDEX
    Explanations

    terms related to pharmacological science

    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
    .usermodel
    -0.07
    Ñĥж
    -0.07
    udio
    -0.06
     GRAT
    -0.06
    uga
    -0.06
    odos
    -0.06
    ugas
    -0.06
     покÑĢÑĭ
    -0.06
    ierz
    -0.06
    amer
    -0.06
    POSITIVE LOGITS
    .nt
    0.07
    bers
    0.07
    maf
    0.06
    vre
    0.06
     Moss
    0.06
    mens
    0.06
    меÑĩ
    0.06
    men
    0.06
    mos
    0.06
     casualty
    0.06
    Activations Density 0.002%

    No Known Activations