© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127100
    Prev
    Next
    INDEX
    Explanations

    negative descriptions of environments or experiences

    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
     urg
    -0.07
    oger
    -0.07
    ediator
    -0.06
    qing
    -0.06
    alin
    -0.06
    tones
    -0.06
     validity
    -0.06
    orp
    -0.06
    ewhat
    -0.06
    wayne
    -0.06
    POSITIVE LOGITS
    _navigation
    0.08
    Navig
    0.07
     joke
    0.07
    اشÛĮ
    0.07
    requ
    0.07
    ä¿Ĺ
    0.06
    ãĥ¼ãĥĪ
    0.06
    pcf
    0.06
    LocalizedMessage
    0.06
     navigating
    0.06
    Activations Density 0.064%

    No Known Activations