© 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. 56776
    Prev
    Next
    INDEX
    Explanations

    variations of the letters "h", "t", and "e", possibly indicating an interest in a certain formatting or typographical element in the text

    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
    ris
    -0.08
    rin
    -0.08
    och
    -0.08
    rint
    -0.08
    rani
    -0.08
    rist
    -0.07
    ray
    -0.07
    rico
    -0.07
    r
    -0.07
    rif
    -0.07
    POSITIVE LOGITS
    ìľ¨
    0.07
    åĭ¢
    0.07
    eton
    0.07
    åĬ¿
    0.07
    spiel
    0.07
    sume
    0.07
    elligence
    0.07
    ackle
    0.06
    entimes
    0.06
    ilda
    0.06
    Activations Density 0.014%

    No Known Activations