© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 1387
    Prev
    Next
    INDEX
    Explanations

    references to late-night talk shows and their hosts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    eren
    -0.06
     tar
    -0.06
     mobil
    -0.06
    olor
    -0.06
    agine
    -0.06
    ered
    -0.05
     Getty
    -0.05
    mani
    -0.05
     weekend
    -0.05
    resse
    -0.05
    POSITIVE LOGITS
    owi
    0.08
     host
    0.07
     laten
    0.07
     hosts
    0.07
    ServletRequest
    0.07
     entertain
    0.07
     Hosting
    0.07
    Fuse
    0.07
     Comedy
    0.07
     nightly
    0.07
    Activations Density 0.016%

    No Known Activations