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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 41363
    Prev
    Next
    INDEX
    Explanations

    references to television 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
    iple
    -0.07
    .scalablytyped
    -0.06
    ADIO
    -0.06
    anoia
    -0.06
    argon
    -0.06
    iples
    -0.06
     mobil
    -0.06
    hra
    -0.06
    ebilecek
    -0.06
    (cd
    -0.06
    POSITIVE LOGITS
     nightly
    0.08
     hosts
    0.08
     host
    0.08
    -night
    0.08
     Comedy
    0.07
     Tonight
    0.07
    Fuse
    0.07
    -host
    0.07
    ÎŃλ
    0.07
     Overnight
    0.07
    Activations Density 0.019%

    No Known Activations