© 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 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. 86001
    Prev
    Next
    INDEX
    Explanations

    references to email and electronic communication

    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
     latter
    -0.08
    s
    -0.07
    ogn
    -0.07
    kinson
    -0.07
    ede
    -0.06
    Ìģ
    -0.06
    esto
    -0.06
    าย
    -0.06
    894
    -0.06
     ÐļÑĢа
    -0.06
    POSITIVE LOGITS
    chimp
    0.08
    ataka
    0.07
    ¶Į
    0.07
    /Web
    0.07
    axis
    0.07
    ing
    0.07
    nya
    0.07
    دا
    0.07
    implify
    0.07
    .IsNullOr
    0.07
    Activations Density 0.003%

    No Known Activations