© 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. 26747
    Prev
    Next
    INDEX
    Explanations

    terms related to processes and mechanisms in various systems

    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
    odel
    -0.08
    okud
    -0.07
    607
    -0.07
    otos
    -0.07
    ynos
    -0.07
    raya
    -0.07
    606
    -0.07
    612
    -0.07
    rets
    -0.06
    icle
    -0.06
    POSITIVE LOGITS
    inx
    0.08
    /on
    0.07
    isme
    0.07
    /post
    0.06
    /in
    0.06
    ngrx
    0.06
    -inter
    0.06
    еÑĢе
    0.06
    _memcpy
    0.06
    izedName
    0.06
    Activations Density 0.041%

    No Known Activations