© 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. 95212
    Prev
    Next
    INDEX
    Explanations

    statements regarding evaluations of performance or treatment

    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
    nnen
    -0.08
    ijing
    -0.07
    ½
    -0.07
    ieber
    -0.07
    tel
    -0.06
    женÑĮ
    -0.06
     Novel
    -0.06
    672
    -0.06
    ený
    -0.06
     novel
    -0.06
    POSITIVE LOGITS
    avax
    0.08
     nor
    0.07
    bang
    0.07
    転
    0.07
     or
    0.07
    едж
    0.06
    AUSE
    0.06
    ause
    0.06
    лин
    0.06
    kanı
    0.06
    Activations Density 0.018%

    No Known Activations