© 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. 124248
    Prev
    Next
    INDEX
    Explanations

    references to brewing and organic farming practices

    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
    íĿ¥
    -0.07
    angler
    -0.07
    RefCount
    -0.07
    referrer
    -0.07
    stial
    -0.07
     Noon
    -0.06
    иÑĤа
    -0.06
    _energy
    -0.06
    kees
    -0.06
    abajo
    -0.06
    POSITIVE LOGITS
     oak
    0.07
    Oak
    0.07
    ose
    0.07
    PDO
    0.06
    åľ¨åľ°
    0.06
     organ
    0.06
     Oak
    0.06
    uce
    0.06
     micro
    0.06
     vintage
    0.06
    Activations Density 0.006%

    No Known Activations