© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 129152
    Prev
    Next
    INDEX
    Explanations

    references to "nerds" and related terminology

    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
    aires
    -0.06
     Elem
    -0.06
    meno
    -0.06
    FW
    -0.06
    cheng
    -0.06
    uncture
    -0.06
    ator
    -0.06
    OLS
    -0.06
    oit
    -0.06
     Murray
    -0.06
    POSITIVE LOGITS
    iness
    0.10
    اÙĨÙĩ
    0.09
    ery
    0.08
    /ge
    0.08
    iest
    0.08
    ERY
    0.08
    ishly
    0.07
    linger
    0.07
    /math
    0.07
    assin
    0.07
    Activations Density 0.007%

    No Known Activations