© 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. 14333
    Prev
    Next
    INDEX
    Explanations

    references to performance and stage presence

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     doma
    -0.07
    414
    -0.07
    ambi
    -0.07
    awi
    -0.06
    tty
    -0.06
    emu
    -0.06
    ileo
    -0.06
     Fast
    -0.06
    anos
    -0.06
    наÑĢÑĥж
    -0.06
    POSITIVE LOGITS
     entrance
    0.08
     entrances
    0.08
    uman
    0.07
     introdu
    0.07
     introduction
    0.07
     slowly
    0.07
     Intro
    0.07
    ãĥ¼ãĥŀ
    0.07
     Entrance
    0.07
     Burr
    0.06
    Activations Density 0.022%

    No Known Activations