© 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. 108044
    Prev
    Next
    INDEX
    Explanations

    references to popular television shows and discussions about their content

    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
    ائÙĩ
    -0.06
     Influ
    -0.06
    terminal
    -0.06
    aub
    -0.06
    rary
    -0.06
     Congress
    -0.06
    .CL
    -0.05
    haf
    -0.05
    زÙĦ
    -0.05
    aż
    -0.05
    POSITIVE LOGITS
    pedia
    0.06
    =yes
    0.06
    å®ľ
    0.06
    ubber
    0.06
    CONTENT
    0.06
    ogi
    0.06
    ERO
    0.06
     putas
    0.06
    inger
    0.06
     vandal
    0.06
    Activations Density 0.003%

    No Known Activations