© 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. 42671
    Prev
    Next
    INDEX
    Explanations

    descriptors related to animated or fantastical films and their qualities

    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
    ãĥ¡ãĥ³ãĥĪ
    -0.07
    VOKE
    -0.07
    вад
    -0.07
    åĥį
    -0.07
    iscard
    -0.07
    essler
    -0.06
    ÄįenÃŃ
    -0.06
    Ñıд
    -0.06
    iesta
    -0.06
    prit
    -0.06
    POSITIVE LOGITS
     leider
    0.08
     too
    0.07
     unfortunately
    0.07
     mostly
    0.06
     Unfortunately
    0.06
     disappointing
    0.06
    oret
    0.06
     deliver
    0.06
    Reviewed
    0.06
     disappoint
    0.06
    Activations Density 0.041%

    No Known Activations