© 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. 126387
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce sourced information or assertions

    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
    shed
    -0.08
     зави
    -0.07
    Ìģt
    -0.07
    itmap
    -0.07
    hani
    -0.07
    .ua
    -0.07
    殿
    -0.07
    .Companion
    -0.07
    ventory
    -0.07
    raig
    -0.07
    POSITIVE LOGITS
    ese
    0.07
    ach
    0.07
    ago
    0.06
    ame
    0.06
     Luke
    0.06
    238
    0.06
    -hand
    0.05
     Greene
    0.05
     Wol
    0.05
    °
    0.05
    Activations Density 0.018%

    No Known Activations