© 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. 103864
    Prev
    Next
    INDEX
    Explanations

    references to names and spelling variations

    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
     unnamed
    -0.07
     improvis
    -0.06
     FALL
    -0.06
    ept
    -0.06
    amd
    -0.06
    ford
    -0.06
    umph
    -0.06
     cyclic
    -0.06
    elling
    -0.06
     meaning
    -0.05
    POSITIVE LOGITS
     variant
    0.09
     ваÑĢианÑĤ
    0.08
     spelling
    0.08
     Renders
    0.08
     variations
    0.08
    alternate
    0.08
    _altern
    0.08
    æĭ¼
    0.07
     variants
    0.07
    variant
    0.07
    Activations Density 0.011%

    No Known Activations