© 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. 116567
    Prev
    Next
    INDEX
    Explanations

    phrases related to positive experiences and recommendations in film

    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
    ustos
    -0.06
    finally
    -0.06
    iken
    -0.06
     finally
    -0.06
     selected
    -0.06
    _traits
    -0.05
     Crunch
    -0.05
     ideal
    -0.05
    END
    -0.05
    ingu
    -0.05
    POSITIVE LOGITS
     ún
    0.08
    imetype
    0.08
    \views
    0.07
     queryInterface
    0.07
     cog
    0.07
     throughout
    0.07
    ãĥ¼ãĤ¯
    0.07
     highlight
    0.07
    erot
    0.07
    _ISR
    0.07
    Activations Density 0.021%

    No Known Activations