© 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. 74681
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to tourist attractions and historical sites

    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
     format
    -0.07
    áš
    -0.06
    erland
    -0.06
     ä¸ĵ
    -0.06
     Dann
    -0.06
     Notices
    -0.06
    ony
    -0.06
    idget
    -0.06
    祥
    -0.06
     gere
    -0.06
    POSITIVE LOGITS
    hoot
    0.07
    OOM
    0.07
    igure
    0.07
     Complex
    0.07
    arak
    0.07
    legen
    0.06
    yr
    0.06
    cales
    0.06
    noon
    0.06
    #End
    0.06
    Activations Density 0.027%

    No Known Activations