© 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. 14760
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to understanding and interpretation

    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
    ὸ
    -0.08
    achinery
    -0.08
    egers
    -0.07
    ARB
    -0.07
    etine
    -0.07
    oleÄį
    -0.07
    opyright
    -0.07
    urrect
    -0.07
    izr
    -0.07
    기를
    -0.07
    POSITIVE LOGITS
     (
    0.07
     or
    0.07
    íķĺëĭ¤
    0.07
    ;
    0.06
    aka
    0.06
    Ł
    0.06
     Sche
    0.06
    wert
    0.06
     something
    0.05
     или
    0.05
    Activations Density 0.033%

    No Known Activations