© 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 EvalsExportsinterp-engineNEWAPI 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. 104610
    Prev
    Next
    INDEX
    Explanations

    terms related to innovation and technology advancements

    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
    ubi
    -0.06
    .sd
    -0.06
    521
    -0.06
    osit
    -0.06
    adem
    -0.06
    ungle
    -0.06
    ismet
    -0.06
    thro
    -0.05
    uzzi
    -0.05
    switch
    -0.05
    POSITIVE LOGITS
     traditional
    0.08
    eph
    0.08
     altogether
    0.07
     conventional
    0.07
    igue
    0.07
     Traditional
    0.07
     parad
    0.07
    traditional
    0.07
    alcon
    0.07
     traditionally
    0.07
    Activations Density 0.032%

    No Known Activations