© 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. 5-LLAMASCOPE-RES-131K
    6. 125510
    Prev
    Next
    INDEX
    Explanations

    numeric terms and structured steps or instructions typically associated with guides or processes

    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
    itas
    -0.07
    vala
    -0.06
    enza
    -0.06
     count
    -0.06
    ron
    -0.06
    point
    -0.06
    atto
    -0.06
     char
    -0.06
    agua
    -0.06
    åĪ·
    -0.06
    POSITIVE LOGITS
    isci
    0.07
    UPER
    0.07
    .Predicate
    0.06
     ì¢ĭìķĦ
    0.06
    igers
    0.06
    вÑģÑı
    0.06
    ystore
    0.06
    .chapter
    0.06
    Rio
    0.06
    edik
    0.06
    Activations Density 0.004%

    No Known Activations