© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 96979
    Prev
    Next
    INDEX
    Explanations

    references to reality television shows and their contestants

    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
    ระ
    -0.08
    metro
    -0.08
     Ziel
    -0.07
    urity
    -0.07
    еж
    -0.07
    ileo
    -0.07
    па
    -0.07
    ег
    -0.07
    ê¹Į
    -0.07
    cÃŃ
    -0.06
    POSITIVE LOGITS
     PageSize
    0.06
    628
    0.06
    èĶµ
    0.06
    PED
    0.06
    irk
    0.06
    trak
    0.06
    atted
    0.06
    aken
    0.06
    notated
    0.05
    ÑĢал
    0.05
    Activations Density 0.002%

    No Known Activations