© 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. 15-LLAMASCOPE-RES-131K
    11. 978
    Prev
    Next
    INDEX
    Explanations

    phrases indicating user consent or agreement regarding terms and conditions

    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
    uster
    -0.07
    iu
    -0.07
    ÇIJ
    -0.07
    uze
    -0.06
    γÏī
    -0.06
    ularity
    -0.06
    um
    -0.06
    arker
    -0.06
    ulty
    -0.06
    ën
    -0.06
    POSITIVE LOGITS
    oca
    0.07
    isd
    0.07
     abide
    0.07
    #ab
    0.07
    stro
    0.07
     ab
    0.07
    isay
    0.06
    entr
    0.06
    ãĥ¼ãĤ¿
    0.06
    ÛĮدا
    0.06
    Activations Density 0.002%

    No Known Activations