© 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. 15-LLAMASCOPE-RES-131K
    11. 87465
    Prev
    Next
    INDEX
    Explanations

    references to specific TV shows and their characters

    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
    æ¥ļ
    -0.07
    hangi
    -0.07
    NCY
    -0.07
     Bolt
    -0.07
    -tm
    -0.07
    û
    -0.07
    @student
    -0.06
    /tmp
    -0.06
    bourg
    -0.06
    /display
    -0.06
    POSITIVE LOGITS
     sitcom
    0.07
    emplate
    0.07
     household
    0.07
     duro
    0.06
     mild
    0.06
    ionic
    0.06
     synd
    0.06
     Household
    0.06
     appliance
    0.06
    odian
    0.06
    Activations Density 0.023%

    No Known Activations