© 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. 2228
    Prev
    Next
    INDEX
    Explanations

    calls to action or prompts for further engagement with content

    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
    ero
    -0.07
    elan
    -0.06
    å¥
    -0.06
    ede
    -0.06
    gger
    -0.06
    ¯¯¯¯
    -0.06
    æĬľ
    -0.06
    hev
    -0.06
    erture
    -0.06
    oxic
    -0.06
    POSITIVE LOGITS
    ấm
    0.06
    'gc
    0.06
    ñana
    0.06
     Booker
    0.06
    toupper
    0.06
     Anim
    0.06
     konkrét
    0.06
    Ñģен
    0.06
    _SZ
    0.06
     Powell
    0.06
    Activations Density 0.006%

    No Known Activations