© 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. 77432
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant setbacks or disappointments

    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
    ÃŃrk
    -0.09
    utzer
    -0.09
    .updateDynamic
    -0.09
    liga
    -0.08
    dete
    -0.08
    ابر
    -0.08
    etooth
    -0.08
     authDomain
    -0.08
    GenerationStrategy
    -0.08
    ÚĺÙĩ
    -0.08
    POSITIVE LOGITS
     challenge
    0.07
    hatt
    0.06
     initial
    0.06
     initially
    0.06
     involved
    0.06
    l
    0.06
     was
    0.06
    0.06
     had
    0.06
     lessons
    0.06
    Activations Density 0.000%

    No Known Activations