© 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. 15-LLAMASCOPE-RES-131K
    11. 88820
    Prev
    Next
    INDEX
    Explanations

    quantitative ratings or scores related to content

    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
    ãĥªãĥ¼
    -0.07
     Lesser
    -0.07
    wers
    -0.06
     dem
    -0.06
    azor
    -0.06
    úc
    -0.06
    mesh
    -0.06
    zw
    -0.06
    WithString
    -0.06
    uite
    -0.06
    POSITIVE LOGITS
    _Tis
    0.08
    itzer
    0.07
    kus
    0.07
    ODO
    0.07
    ADI
    0.07
    _mC
    0.07
    -fontawesome
    0.07
    ë¡ľëĵľ
    0.07
    .ExecuteReader
    0.07
    aylight
    0.07
    Activations Density 0.000%

    No Known Activations