© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 15698
    Prev
    Next
    INDEX
    Explanations

    terms related to networks or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Prefixes or initial parts of company/product names, often appearing in contexts where the business, product, or service is being described or promoted.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    orem
    -0.08
    &M
    -0.08
    notated
    -0.07
    MMdd
    -0.06
    htags
    -0.06
    dere
    -0.06
    #ad
    -0.06
    patibility
    -0.06
    manuel
    -0.06
    anel
    -0.06
    POSITIVE LOGITS
    /her
    0.07
    .reflect
    0.07
    actly
    0.07
    ses
    0.06
     ochran
    0.06
    RNA
    0.06
     jsonObj
    0.06
    _cast
    0.06
    inear
    0.06
    ERSION
    0.06
    Activations Density 0.099%

    No Known Activations