© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 91848
    Prev
    Next
    INDEX
    Explanations

    references to first experiences or initial creations

    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
    cher
    -0.07
     Bol
    -0.07
    chan
    -0.07
    ">//
    -0.07
    occasion
    -0.06
    æ½
    -0.06
    ĥ½
    -0.06
     jue
    -0.06
    bol
    -0.06
    _called
    -0.06
    POSITIVE LOGITS
     ever
    0.08
     tiên
    0.08
    -ever
    0.07
    cept
    0.06
     alphabetical
    0.06
     chronological
    0.06
    å¤ķ
    0.06
    viron
    0.06
    andum
    0.06
     EVER
    0.06
    Activations Density 0.016%

    No Known Activations