© 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. 17-LLAMASCOPE-RES-131K
    11. 94248
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "you are" or its variations

    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
    onis
    -0.07
    eton
    -0.07
    ãģ¾
    -0.07
    haven
    -0.06
    .getValueAt
    -0.06
    UGIN
    -0.06
    iev
    -0.06
    _OCCURRED
    -0.06
     èŤ
    -0.06
    eten
    -0.06
    POSITIVE LOGITS
     simple
    0.07
    eldo
    0.06
     either
    0.06
     a
    0.06
     or
    0.06
    603
    0.06
     directly
    0.06
    ANI
    0.06
    æł¹æľ¬
    0.06
     nor
    0.06
    Activations Density 0.004%

    No Known Activations