© 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. 73006
    Prev
    Next
    INDEX
    Explanations

    titles of TV shows or movies, particularly those that include significant elements of seasonal or holiday themes

    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
     Minority
    -0.08
    ixture
    -0.07
    lington
    -0.06
    amba
    -0.06
    chk
    -0.06
     Sesso
    -0.06
    ervo
    -0.06
     kills
    -0.06
    åĵ¥
    -0.06
    aces
    -0.06
    POSITIVE LOGITS
    akit
    0.07
     romance
    0.07
    pais
    0.07
     Sweep
    0.07
     Christmas
    0.07
    chluss
    0.07
    _US
    0.06
    Hope
    0.06
    Pure
    0.06
    uron
    0.06
    Activations Density 0.022%

    No Known Activations