© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 2849
    Prev
    Next
    INDEX
    Explanations

    numerical values or identifiers

    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
    ictures
    -0.06
    structors
    -0.06
    omi
    -0.06
    мини
    -0.06
    utes
    -0.06
    quals
    -0.06
    ढ
    -0.06
    azor
    -0.06
    <Scalar
    -0.06
    unner
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĥĩ
    0.06
    Filename
    0.06
    ãĥ¼ãĥľ
    0.06
    AIM
    0.06
    pard
    0.06
    ãĤ¥
    0.06
    nbsp
    0.06
    ODO
    0.05
    oplayer
    0.05
     Raid
    0.05
    Activations Density 0.007%

    No Known Activations