© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 93494
    Prev
    Next
    INDEX
    Explanations

    numerical values or important numerical data

    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
    ifton
    -0.07
    oil
    -0.07
    á»ĩn
    -0.07
    à¥įतव
    -0.07
    оÑĤв
    -0.06
     ÑģÑĤа
    -0.06
    lest
    -0.06
     taraf
    -0.06
    .TR
    -0.06
    ÏĢοÏį
    -0.06
    POSITIVE LOGITS
     Gia
    0.07
    hazi
    0.07
    UTDOWN
    0.06
    ¸ı
    0.06
    ALCHEMY
    0.06
    iap
    0.06
     Sof
    0.06
     Innoc
    0.06
    اة
    0.05
    ÙģÙĩÙĪÙħ
    0.05
    Activations Density 0.000%

    No Known Activations