© 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. 27092
    Prev
    Next
    INDEX
    Explanations

    specific numerical identifiers or codes related to regulations and legal provisions

    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
    tridge
    -0.06
     Ae
    -0.06
    ied
    -0.06
    欲
    -0.05
     Yön
    -0.05
    546
    -0.05
    ingleton
    -0.05
     nale
    -0.05
    mpl
    -0.05
    aland
    -0.05
    POSITIVE LOGITS
    ernen
    0.07
     Credits
    0.07
     hữu
    0.06
    ãĥĩãĤ£ãĤ¢
    0.06
    elyn
    0.06
    .BackgroundImageLayout
    0.06
    _CHIP
    0.06
    ancement
    0.06
    toBeDefined
    0.06
    Sensitive
    0.06
    Activations Density 0.013%

    No Known Activations