© 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. 2042
    Prev
    Next
    INDEX
    Explanations

    specific nouns and related terms that indicate key elements in a narrative or explanation

    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
    adal
    -0.07
    ague
    -0.06
    aga
    -0.06
    eps
    -0.06
    its
    -0.06
    _VOID
    -0.06
     meaning
    -0.06
     account
    -0.06
    cho
    -0.06
    thes
    -0.06
    POSITIVE LOGITS
     which
    0.10
    which
    0.10
     który
    0.09
     mÃł
    0.08
     whose
    0.08
     nÃło
    0.08
     اÙĦØ°ÙĬ
    0.08
     tiener
    0.08
     cui
    0.08
     اÙĦتÙĬ
    0.07
    Activations Density 0.071%

    No Known Activations