© 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. 15-LLAMASCOPE-RES-131K
    11. 35
    Prev
    Next
    INDEX
    Explanations

    phrases that highlight potential challenges or problems associated with specific topics

    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
    chaft
    -0.07
    ustomed
    -0.06
    vl
    -0.06
    aigned
    -0.06
    icas
    -0.06
    alet
    -0.06
     célib
    -0.06
    culus
    -0.06
    ivos
    -0.06
    ios
    -0.05
    POSITIVE LOGITS
     ones
    0.09
    ones
    0.09
    %B
    0.07
    others
    0.06
     mı
    0.06
     perhaps
    0.06
    óż
    0.06
    .native
    0.06
    ÑĢип
    0.06
     Ones
    0.06
    Activations Density 0.008%

    No Known Activations