© 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. 78691
    Prev
    Next
    INDEX
    Explanations

    references to the global context or issues faced by nations

    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
    zelf
    -0.08
    elor
    -0.08
    eters
    -0.07
    imson
    -0.07
    ootball
    -0.07
    že
    -0.07
    è¼Ŀ
    -0.07
    گاÙĩ
    -0.07
    ety
    -0.07
    coni
    -0.07
    POSITIVE LOGITS
    -wide
    0.14
    Wide
    0.13
    wide
    0.12
     wide
    0.10
     Wide
    0.10
    /world
    0.10
    liness
    0.10
    views
    0.10
    weit
    0.10
    -ren
    0.09
    Activations Density 0.074%

    No Known Activations