© 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. 75100
    Prev
    Next
    INDEX
    Explanations

    words related to assistance or help

    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
    ias
    -0.07
    ahi
    -0.07
    æĿī
    -0.06
    ncy
    -0.06
    esy
    -0.06
    quis
    -0.06
    iew
    -0.06
    oblins
    -0.06
    à¹Ħà¸Ľ
    -0.06
    nt
    -0.06
    POSITIVE LOGITS
    eza
    0.07
    oli
    0.06
    .SwingConstants
    0.06
     Oz
    0.06
    lif
    0.06
    ereg
    0.06
    ulling
    0.06
     Tropical
    0.06
    yang
    0.06
    andex
    0.06
    Activations Density 0.002%

    No Known Activations