© 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. 117683
    Prev
    Next
    INDEX
    Explanations

    patterns or associations of words that relate to various descriptors or attributes

    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
    jte
    -0.07
    oni
    -0.06
     princip
    -0.06
    lsi
    -0.06
    atti
    -0.06
    ATION
    -0.06
    enci
    -0.06
    loff
    -0.06
    brace
    -0.06
     Nim
    -0.06
    POSITIVE LOGITS
     éķ·
    0.06
    indered
    0.06
     moth
    0.06
    ktor
    0.06
     Hag
    0.06
    رش
    0.06
    ган
    0.06
    631
    0.06
     Moran
    0.06
    uento
    0.06
    Activations Density 0.009%

    No Known Activations