© 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. 9-LLAMASCOPE-RES-131K
    11. 98347
    Prev
    Next
    INDEX
    Explanations

    terms associated with cannabis and its chemical properties

    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
    agram
    -0.07
    Ãłng
    -0.07
    кав
    -0.06
    enity
    -0.06
    lena
    -0.06
    ennie
    -0.06
    ritte
    -0.06
    rå
    -0.06
    itta
    -0.06
     Jewel
    -0.06
    POSITIVE LOGITS
     Affero
    0.08
    liš
    0.07
    á»ī
    0.06
     Sesso
    0.06
    ãĤ¹ãĥ¬
    0.06
    GLOSS
    0.06
    ãĢ
    0.06
    INY
    0.06
    ãĥĸãĥ©
    0.06
    UFF
    0.06
    Activations Density 0.056%

    No Known Activations