© 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. 17-LLAMASCOPE-RES-131K
    11. 57409
    Prev
    Next
    INDEX
    Explanations

    references to "geek" culture or vocabulary

    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
    ÅĻe
    -0.07
    ocl
    -0.06
    orsi
    -0.06
    arity
    -0.06
    ên
    -0.06
    overe
    -0.06
    mak
    -0.06
    nie
    -0.06
    ÑĢак
    -0.06
    mel
    -0.06
    POSITIVE LOGITS
    ishly
    0.09
    iest
    0.08
    ernet
    0.08
    iverse
    0.08
    ery
    0.07
    omm
    0.07
    anical
    0.07
    ayette
    0.07
    yg
    0.07
    y
    0.07
    Activations Density 0.002%

    No Known Activations