© 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. 40083
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a positive reaction or approval

    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
    aid
    -0.06
    oppable
    -0.06
    illis
    -0.06
    weetalert
    -0.06
     tongue
    -0.06
    uffy
    -0.06
    ëł
    -0.05
     Eclipse
    -0.05
    æĹıèĩªæ²»
    -0.05
    ιοÏĤ
    -0.05
    POSITIVE LOGITS
     much
    0.07
    Æ°á»Ľ
    0.07
    .bo
    0.06
    ẹn
    0.06
    oha
    0.06
    uco
    0.06
     cries
    0.06
     mutual
    0.06
     great
    0.06
     trú
    0.06
    Activations Density 0.021%

    No Known Activations