© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84098
    Prev
    Next
    INDEX
    Explanations

    expressions of boredom or disinterest

    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
    iasi
    -0.07
    ovolta
    -0.06
    amik
    -0.06
     Decomp
    -0.06
    ฤ
    -0.06
    uba
    -0.06
    alley
    -0.06
    IFO
    -0.06
     metav
    -0.06
    iac
    -0.06
    POSITIVE LOGITS
     boring
    0.21
     boredom
    0.19
     bored
    0.18
     bore
    0.18
     dull
    0.12
     tedious
    0.10
     yaw
    0.10
     enn
    0.10
     dr
    0.09
     monot
    0.09
    Activations Density 0.149%

    No Known Activations