© 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. 28881
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or acknowledgment

    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
    anchor
    -0.06
    Anchor
    -0.06
     Anchor
    -0.06
    erts
    -0.06
    ani
    -0.06
    uchi
    -0.06
    anno
    -0.06
    ada
    -0.06
    avirus
    -0.06
    or
    -0.05
    POSITIVE LOGITS
    ebek
    0.09
     courtesy
    0.08
     alert
    0.07
     alerted
    0.07
    alert
    0.07
     via
    0.07
     pointed
    0.06
    thanks
    0.06
    èm
    0.06
     à¹Ģà¸Ĥà¸ķ
    0.06
    Activations Density 0.015%

    No Known Activations