© 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. 16277
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or thankfulness, particularly towards a deity

    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
    thon
    -0.07
     å¹
    -0.07
    umo
    -0.07
    collapsed
    -0.06
    atcher
    -0.06
    миÑĢ
    -0.06
    zel
    -0.06
    an
    -0.06
    овÑĸд
    -0.06
    ossible
    -0.06
    POSITIVE LOGITS
    hic
    0.07
    ephy
    0.07
     for
    0.06
    unte
    0.06
    itial
    0.06
     forbid
    0.06
    owns
    0.06
    ABCDEFGHIJKLMNOP
    0.06
     migr
    0.06
    .opend
    0.06
    Activations Density 0.002%

    No Known Activations