© 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. 108722
    Prev
    Next
    INDEX
    Explanations

    expressions related to communication, especially in contexts of loss or misunderstanding

    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
    .yy
    -0.09
    ollen
    -0.08
    awe
    -0.08
     Kraj
    -0.07
    COMPARE
    -0.07
    xeb
    -0.07
    braco
    -0.07
    figcaption
    -0.07
    ково
    -0.07
    ç®±
    -0.07
    POSITIVE LOGITS
     someone
    0.08
     or
    0.06
     conver
    0.06
     somebody
    0.06
     Holt
    0.05
    someone
    0.05
     involving
    0.05
     Physical
    0.05
    Topic
    0.05
     something
    0.05
    Activations Density 0.027%

    No Known Activations