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

    Neuronpedia

    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. 95410
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "live" in various forms

    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
    eut
    -0.07
    ../../../
    -0.07
    aly
    -0.06
    aroo
    -0.06
    aten
    -0.06
    als
    -0.06
    sembl
    -0.06
    omaly
    -0.06
    ollapse
    -0.06
    pling
    -0.06
    POSITIVE LOGITS
    ÏįÏĢ
    0.07
    iting
    0.07
    UILTIN
    0.07
    _COMPILER
    0.07
    boat
    0.07
    .setPrototypeOf
    0.07
    illisecond
    0.06
    ialis
    0.06
    bracht
    0.06
    .opensource
    0.06
    Activations Density 0.025%

    No Known Activations