© 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. 54821
    Prev
    Next
    INDEX
    Explanations

    elements of satire and parody in text

    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
    ergarten
    -0.07
    elijk
    -0.06
    StateManager
    -0.06
    inars
    -0.06
    zan
    -0.06
    ensed
    -0.06
    aff
    -0.06
    abox
    -0.06
    436
    -0.06
    mel
    -0.06
    POSITIVE LOGITS
    /mock
    0.09
    ously
    0.07
    COPE
    0.07
    ishly
    0.07
    geist
    0.06
    ingly
    0.06
    tainment
    0.06
    libc
    0.06
    æľĭ
    0.06
     schn
    0.06
    Activations Density 0.007%

    No Known Activations