© 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. 17-LLAMASCOPE-RES-131K
    11. 88890
    Prev
    Next
    INDEX
    Explanations

    quantifiable metrics and data related to production and processing

    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
    /license
    -0.06
    (?:
    -0.06
    ule
    -0.06
    è
    -0.06
    ua
    -0.06
     congress
    -0.06
    wo
    -0.06
    uard
    -0.06
    çİĩ
    -0.05
    å¹
    -0.05
    POSITIVE LOGITS
    abox
    0.08
    leaning
    0.07
    ëŀij
    0.07
    tuk
    0.07
    .Execution
    0.06
    elic
    0.06
    Containing
    0.06
    ÑĥÑĪки
    0.06
    ëĿ½
    0.06
    oking
    0.06
    Activations Density 0.023%

    No Known Activations