© 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. 118966
    Prev
    Next
    INDEX
    Explanations

    phrases related to disagreements and resignations

    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
    óng
    -0.07
    IMIT
    -0.07
    /Gate
    -0.07
    کرÛĮ
    -0.06
     باÛĮ
    -0.06
    تÙĪ
    -0.06
    ì¸ł
    -0.06
    ktor
    -0.06
    utsch
    -0.06
     subrange
    -0.06
    POSITIVE LOGITS
     too
    0.09
     Too
    0.09
     irre
    0.08
     TOO
    0.08
    Too
    0.08
    too
    0.07
     ins
    0.07
    å®ŀåľ¨
    0.07
    太
    0.07
    Ñģли
    0.06
    Activations Density 0.050%

    No Known Activations