© 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. 22-LLAMASCOPE-RES-131K
    11. 3807
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'T' in various contexts

    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
    anche
    -0.07
    our
    -0.07
    orry
    -0.06
    ierge
    -0.06
    asInstanceOf
    -0.06
    ro
    -0.06
    uple
    -0.06
     Triple
    -0.06
    ube
    -0.06
    icker
    -0.06
    POSITIVE LOGITS
     ske
    0.07
    иÑģк
    0.07
    -Men
    0.07
    arent
    0.06
    iare
    0.06
    _OPTION
    0.06
    .ActionListener
    0.06
    antor
    0.06
    lá
    0.06
    enerator
    0.06
    Activations Density 0.015%

    No Known Activations