© 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. 79153
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Fernando" and its variations

    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
    perience
    -0.07
    dem
    -0.07
     âĸĪâĸĪ
    -0.07
    xac
    -0.07
    iteration
    -0.07
    elig
    -0.07
    ød
    -0.07
    ewater
    -0.06
    asury
    -0.06
    errupt
    -0.06
    POSITIVE LOGITS
    ÑĢави
    0.06
    eding
    0.06
    ebra
    0.06
    rale
    0.06
     Weather
    0.06
     Hao
    0.06
    ¡
    0.06
    reich
    0.06
    âĶĢ
    0.06
    ández
    0.06
    Activations Density 0.005%

    No Known Activations