© 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. 74744
    Prev
    Next
    INDEX
    Explanations

    expressions of inclusivity and commonality across different experiences and backgrounds

    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
    uter
    -0.06
     Circular
    -0.05
    struct
    -0.05
    orts
    -0.05
    and
    -0.05
    orean
    -0.05
     stuff
    -0.05
     Basis
    -0.05
     (
    -0.05
    ele
    -0.05
    POSITIVE LOGITS
     lĩnh
    0.08
    ढ
    0.08
     nues
    0.08
    .big
    0.07
    âĹĭ
    0.07
    ãĢĤ↵↵↵↵↵↵
    0.07
    507
    0.07
    BackStack
    0.07
    ://%
    0.07
    eroon
    0.07
    Activations Density 0.015%

    No Known Activations