© 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. 63153
    Prev
    Next
    INDEX
    Explanations

    references to official titles or entities, particularly in a governmental context

    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
    ault
    -0.07
    azor
    -0.07
     teen
    -0.06
    è¡¡
    -0.06
    _hw
    -0.06
    Ñħод
    -0.06
     Lanc
    -0.06
    .flex
    -0.06
    chi
    -0.06
    ihu
    -0.06
    POSITIVE LOGITS
     following
    0.09
    purpose
    0.07
    ugas
    0.07
    following
    0.07
    ittel
    0.07
    oru
    0.06
    OutOfBoundsException
    0.06
     purpose
    0.06
    ãĥīãĥ«
    0.06
     Following
    0.06
    Activations Density 0.057%

    No Known Activations