© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127475
    Prev
    Next
    INDEX
    Explanations

    variations of the word "express" and its forms 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
    deaux
    -0.08
    ῦ
    -0.07
    chl
    -0.07
    FileVersion
    -0.07
    LocalizedMessage
    -0.07
    ÅĻeh
    -0.07
    Rus
    -0.07
    ;br
    -0.07
    chein
    -0.07
     FLASH
    -0.07
    POSITIVE LOGITS
     nor
    0.07
     or
    0.06
    ly
    0.06
    t
    0.06
    åħ°
    0.06
    tt
    0.05
    lá
    0.05
    orb
    0.05
    Visit
    0.05
    ted
    0.05
    Activations Density 0.001%

    No Known Activations