© 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. 832
    Prev
    Next
    INDEX
    Explanations

    terms related to legal disputes and claims

    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
    asia
    -0.07
    lap
    -0.07
    ATH
    -0.07
     pás
    -0.07
    uro
    -0.06
    Ñĥки
    -0.06
    pron
    -0.06
    ãĥĸãĥª
    -0.06
     Rath
    -0.06
     operational
    -0.06
    POSITIVE LOGITS
    _UNS
    0.07
    æ´¾
    0.07
    asco
    0.07
    amax
    0.06
     civ
    0.06
    ÛĮÙĩ
    0.06
     uncert
    0.06
    OrNil
    0.06
    arness
    0.06
    uez
    0.06
    Activations Density 0.004%

    No Known Activations