© 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. 9-LLAMASCOPE-RES-131K
    11. 95598
    Prev
    Next
    INDEX
    Explanations

    references to body structures or physical forms

    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
    obot
    -0.08
    ocuk
    -0.08
    obb
    -0.08
    odb
    -0.07
    checker
    -0.06
    ió
    -0.06
    incinn
    -0.06
     ãģĹ
    -0.06
    bir
    -0.06
    691
    -0.06
    POSITIVE LOGITS
    atz
    0.07
    Untitled
    0.06
     Oliv
    0.06
    uron
    0.06
     Plex
    0.06
    ãģļ
    0.06
    GST
    0.06
    MOD
    0.05
     Hague
    0.05
    iller
    0.05
    Activations Density 0.001%

    No Known Activations