© 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. 57665
    Prev
    Next
    INDEX
    Explanations

    themes related to social issues and challenges

    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
    âĢ¦↵
    -0.09
    ...↵
    -0.06
    âĢ¦
    -0.06
    âĢ¦”
    -0.06
    ..↵
    -0.06
     Customs
    -0.06
     âĢ¦↵
    -0.06
    .↵
    -0.05
     “
    -0.05
     actually
    -0.05
    POSITIVE LOGITS
     modne
    0.09
    IIIK
    0.08
    _OCCURRED
    0.08
    _TAC
    0.08
    _OW
    0.08
    .Done
    0.08
    .scalablytyped
    0.08
    zı
    0.08
    leh
    0.08
    /lic
    0.08
    Activations Density 0.001%

    No Known Activations