© 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. 124592
    Prev
    Next
    INDEX
    Explanations

    segments of code dealing with serialization and data loading functions

    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
     UNIVERS
    -0.09
    sez
    -0.07
    ëĭ¤ê°Ģ
    -0.07
    universal
    -0.07
    Campo
    -0.07
     LENG
    -0.07
    APPER
    -0.07
    ìĬ¤ì½Ķ
    -0.07
    ses
    -0.07
    peare
    -0.07
    POSITIVE LOGITS
     hol
    0.06
    gne
    0.06
    å£
    0.05
    igious
    0.05
    kol
    0.05
     Uncategorized
    0.05
    hol
    0.05
     \↵
    0.05
     net
    0.05
    -gnu
    0.05
    Activations Density 0.009%

    No Known Activations