© 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. 120318
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to comedy

    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
     Emerson
    -0.08
    åĽ³
    -0.07
    bage
    -0.07
     trÆ°á»Łng
    -0.07
    conds
    -0.07
    ill
    -0.07
    utenberg
    -0.07
    en
    -0.07
    idl
    -0.07
     McCartney
    -0.06
    POSITIVE LOGITS
    tainment
    0.07
    ¤¤
    0.07
     Stap
    0.07
    timing
    0.06
    /music
    0.06
    town
    0.06
    101
    0.06
     Relief
    0.06
    365
    0.06
    âĶĶ
    0.06
    Activations Density 0.009%

    No Known Activations