© 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. 74295
    Prev
    Next
    INDEX
    Explanations

    questions or phrases that inquire about possibilities or hypothetical scenarios

    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
    ¶Į
    -0.06
    ativa
    -0.06
    oner
    -0.06
    ãĥ¼ãĥĦ
    -0.06
    οκ
    -0.06
    ilinear
    -0.06
    /on
    -0.06
     which
    -0.06
     wich
    -0.06
    bed
    -0.06
    POSITIVE LOGITS
    sis
    0.07
    ynes
    0.07
    opyright
    0.07
    burger
    0.07
    velte
    0.07
    avax
    0.06
     CrossRef
    0.06
    yny
    0.06
    Bounding
    0.06
    lei
    0.06
    Activations Density 0.021%

    No Known Activations