© 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. 105975
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to political power dynamics and international relations

    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
    itone
    -0.07
     jezd
    -0.06
    izzo
    -0.06
    çĽ
    -0.06
     зв
    -0.06
    823
    -0.06
    oly
    -0.06
    ERSIST
    -0.06
    UX
    -0.06
     champ
    -0.06
    POSITIVE LOGITS
    ollen
    0.07
    Ø·ÙĦ
    0.07
    á»ĵi
    0.07
    ucht
    0.06
     Programmer
    0.06
     Lod
    0.06
    anian
    0.06
    omor
    0.06
    ÑĥÑħ
    0.06
     Prosper
    0.06
    Activations Density 0.181%

    No Known Activations