© 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. 9-LLAMASCOPE-RES-131K
    11. 95774
    Prev
    Next
    INDEX
    Explanations

    patterns or structures in formatted data or code

    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
    alls
    -0.08
    å³
    -0.07
    oog
    -0.07
     YÃĸ
    -0.07
    ober
    -0.07
     Cyr
    -0.07
     âĨĴ↵↵
    -0.07
     eskort
    -0.07
     favour
    -0.06
    εÏħ
    -0.06
    POSITIVE LOGITS
    ë²Į
    0.06
    avy
    0.06
    .digital
    0.06
    _exempt
    0.06
     ro
    0.06
    323
    0.05
    ankan
    0.05
    Violation
    0.05
    .Encode
    0.05
    vik
    0.05
    Activations Density 0.013%

    No Known Activations