© 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. 69130
    Prev
    Next
    INDEX
    Explanations

    references to knowledge and specialized skills in various contexts

    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
    cott
    -0.08
    frey
    -0.07
    load
    -0.07
    ạp
    -0.07
    ino
    -0.07
    ocker
    -0.07
    light
    -0.07
    jing
    -0.07
    ovo
    -0.07
    üz
    -0.07
    POSITIVE LOGITS
    rdf
    0.06
    /memory
    0.06
    /power
    0.06
    dart
    0.06
    es
    0.06
     dor
    0.06
    entence
    0.06
    SSION
    0.06
     gained
    0.06
    sessions
    0.06
    Activations Density 0.007%

    No Known Activations