© 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. 119212
    Prev
    Next
    INDEX
    Explanations

    terms related to automation in various industries

    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
    èĥŀ
    -0.07
    INESS
    -0.07
    /stdc
    -0.07
    ocard
    -0.07
    903
    -0.07
    inator
    -0.07
    orie
    -0.06
    añ
    -0.06
    /resource
    -0.06
    تز
    -0.06
    POSITIVE LOGITS
    ically
    0.08
    ạt
    0.07
    lot
    0.07
    umblr
    0.07
    ally
    0.06
    neum
    0.06
    most
    0.06
    .Var
    0.06
    ates
    0.06
    ther
    0.06
    Activations Density 0.002%

    No Known Activations