© 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. 15-LLAMASCOPE-RES-131K
    11. 103401
    Prev
    Next
    INDEX
    Explanations

    references to materials and products made from leather, particularly those that involve animal hides

    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
    isse
    -0.07
    hetto
    -0.07
     lodging
    -0.07
    /community
    -0.07
    .community
    -0.07
    sson
    -0.07
    /host
    -0.07
     عÙħ
    -0.06
    iese
    -0.06
    glass
    -0.06
    POSITIVE LOGITS
     hides
    0.07
    çļ®
    0.07
    ECTOR
    0.07
     Leather
    0.06
    Ïģη
    0.06
    posix
    0.06
     Skin
    0.06
     Reb
    0.06
    kur
    0.06
    ê°IJ
    0.06
    Activations Density 0.009%

    No Known Activations