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

    Neuronpedia

    Jacobian LensNEW
    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. 59242
    Prev
    Next
    INDEX
    Explanations

    variations of the word "skeptic" or related terms

    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
    ührung
    -0.07
    adera
    -0.07
    074
    -0.07
    kker
    -0.07
    umer
    -0.06
    unner
    -0.06
    SHIP
    -0.06
    mey
    -0.06
    getRepository
    -0.06
    nable
    -0.06
    POSITIVE LOGITS
    PerPixel
    0.07
    vang
    0.07
     Muss
    0.07
    letal
    0.07
    apa
    0.06
    éĥİ
    0.06
    chers
    0.06
    .Framework
    0.06
    ventus
    0.06
    hem
    0.06
    Activations Density 0.028%

    No Known Activations