© 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. 29281
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating magnitude, particularly in terms of quantity or quality

    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
    venge
    -0.07
    Specifier
    -0.06
    maf
    -0.06
    batis
    -0.06
    .undefined
    -0.06
    igy
    -0.06
    άÏģÏĩ
    -0.06
     swingers
    -0.06
    ISTORY
    -0.06
    ortex
    -0.06
    POSITIVE LOGITS
    zens
    0.07
     enough
    0.07
     share
    0.07
     usual
    0.06
    iston
    0.06
    abbit
    0.06
     few
    0.06
     Äijủ
    0.06
     Cann
    0.06
    omb
    0.06
    Activations Density 0.012%

    No Known Activations