© 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. 54103
    Prev
    Next
    INDEX
    Explanations

    phrases that encourage action or motivate the reader to proceed

    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
    lash
    -0.06
    obierno
    -0.06
    ordion
    -0.06
    å¹
    -0.06
    lox
    -0.06
     chod
    -0.06
    culus
    -0.06
    uss
    -0.06
    uhl
    -0.06
    *>*
    -0.05
    POSITIVE LOGITS
    _aliases
    0.07
    ä¿Ĺ
    0.07
    andr
    0.07
    cke
    0.07
    ipped
    0.07
    akan
    0.07
    ays
    0.07
    hare
    0.06
    çķ¥
    0.06
    enumer
    0.06
    Activations Density 0.002%

    No Known Activations