© 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. 87773
    Prev
    Next
    INDEX
    Explanations

    historical figures associated with significant political events or changes

    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
    197
    -0.11
    196
    -0.10
    195
    -0.08
    Û±Û¹Û·
    -0.08
     Mao
    -0.08
     Nixon
    -0.07
    Û±Û¹Û¶
    -0.07
     Highway
    -0.07
     computer
    -0.07
     sevent
    -0.07
    POSITIVE LOGITS
    190
    0.16
    191
    0.16
    189
    0.15
    188
    0.12
    187
    0.10
    192
    0.10
     Sphinx
    0.09
     WW
    0.08
     Titanic
    0.08
     Wireless
    0.08
    Activations Density 0.670%

    No Known Activations