© 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. 116619
    Prev
    Next
    INDEX
    Explanations

    phrases related to examination and certification details

    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
    Ø°
    -0.07
    apol
    -0.07
    isten
    -0.06
    ello
    -0.06
    ranking
    -0.06
    .um
    -0.06
    'field
    -0.06
    олом
    -0.06
    _dimensions
    -0.06
     Bris
    -0.06
    POSITIVE LOGITS
     dumps
    0.07
     Mull
    0.06
    åĬŁ
    0.06
    eydi
    0.06
    mnop
    0.06
     UObject
    0.06
     TestUtils
    0.06
    STITUTE
    0.06
     freopen
    0.06
    erea
    0.06
    Activations Density 0.000%

    No Known Activations