© 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. 17-LLAMASCOPE-RES-131K
    11. 75720
    Prev
    Next
    INDEX
    Explanations

    financial implications or consequences

    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
    olith
    -0.08
    mrt
    -0.07
    /null
    -0.07
    noho
    -0.07
    neas
    -0.07
     automat
    -0.07
    enas
    -0.06
    زÙħ
    -0.06
    kip
    -0.06
    تÙĬ
    -0.06
    POSITIVE LOGITS
    ail
    0.07
    æİĴ
    0.06
    ä¿®
    0.06
     diagnosis
    0.06
     Diagnosis
    0.06
     absorbing
    0.06
    agua
    0.06
    ваÑĢ
    0.06
    ji
    0.06
     tomorrow
    0.06
    Activations Density 0.004%

    No Known Activations