© 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. 17-LLAMASCOPE-RES-131K
    11. 129801
    Prev
    Next
    INDEX
    Explanations

    statements about the properties and effects of food items, particularly vegetables

    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
    ethoven
    -0.10
    anto
    -0.09
    achinery
    -0.09
    tero
    -0.09
    ponse
    -0.08
     DISCLAIM
    -0.08
    PDOException
    -0.08
    menin
    -0.08
    ponible
    -0.08
    zek
    -0.08
    POSITIVE LOGITS
    4
    0.06
    rove
    0.06
    60
    0.05
     nicknamed
    0.05
     Lana
    0.05
     Lesbian
    0.05
    9
    0.05
     because
    0.05
     especially
    0.05
     joined
    0.05
    Activations Density 0.025%

    No Known Activations