© 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. 73374
    Prev
    Next
    INDEX
    Explanations

    documents that discuss various regulations and structural designs related to data and facilities

    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
    LÄ°
    -0.08
    abbo
    -0.08
    andest
    -0.08
    .scalablytyped
    -0.07
    esel
    -0.07
    Æ°Æ¡
    -0.07
    _Tis
    -0.07
     Dank
    -0.07
    iani
    -0.07
    isce
    -0.07
    POSITIVE LOGITS
     two
    0.14
     both
    0.13
     several
    0.12
    two
    0.11
    两个
    0.10
    both
    0.10
     three
    0.09
    åĪĨåĪ«
    0.09
     Both
    0.09
     Two
    0.09
    Activations Density 0.092%

    No Known Activations