© 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. 104044
    Prev
    Next
    INDEX
    Explanations

    references to time periods or changes in status

    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
    оÑĢг
    -0.07
    Ñİ
    -0.06
    ibus
    -0.06
    zial
    -0.06
     Wave
    -0.06
    edi
    -0.06
     Latter
    -0.06
    ambre
    -0.06
    onda
    -0.06
    viz
    -0.06
    POSITIVE LOGITS
    .ends
    0.07
    aight
    0.07
    سÙĪب
    0.07
    بÙĪاسطة
    0.07
    .react
    0.06
    DefaultValue
    0.06
    soon
    0.06
    ãĥ©ãĥ¼
    0.06
    ENTA
    0.06
    -rad
    0.06
    Activations Density 0.000%

    No Known Activations