© 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. 70595
    Prev
    Next
    INDEX
    Explanations

    numerical values and statistics related to organizations and entities

    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
    ushman
    -0.08
    enden
    -0.08
    uiten
    -0.08
    ávÄĽ
    -0.07
    .remote
    -0.07
    hcp
    -0.07
    usz
    -0.07
    orrent
    -0.07
    _phy
    -0.07
    toolbox
    -0.07
    POSITIVE LOGITS
     largest
    0.14
     Largest
    0.11
     leading
    0.11
     world
    0.11
    -largest
    0.11
     oldest
    0.10
     premier
    0.10
    larg
    0.09
    leading
    0.09
     worlds
    0.09
    Activations Density 0.145%

    No Known Activations