© 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. 57021
    Prev
    Next
    INDEX
    Explanations

    negative feelings or experiences related to monotony or boredom

    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
    eba
    -0.06
     Dak
    -0.06
    reamble
    -0.06
     pag
    -0.06
    aca
    -0.05
     Fro
    -0.05
     Hum
    -0.05
     sp
    -0.05
    umo
    -0.05
    ître
    -0.05
    POSITIVE LOGITS
     bored
    0.14
     boredom
    0.13
     boring
    0.13
     repet
    0.11
     bore
    0.10
     repetitive
    0.10
     monot
    0.10
     tired
    0.10
     repetition
    0.09
     bland
    0.09
    Activations Density 0.065%

    No Known Activations