© 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. 3426
    Prev
    Next
    INDEX
    Explanations

    expressions of personal investment and dedication in work

    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
    ihan
    -0.07
    usses
    -0.06
    omic
    -0.06
    acer
    -0.06
     complimentary
    -0.06
     compliment
    -0.05
     habit
    -0.05
    SON
    -0.05
     promise
    -0.05
    ought
    -0.05
    POSITIVE LOGITS
    ionario
    0.07
    หว
    0.07
    léd
    0.07
     derec
    0.07
    ITES
    0.07
    cilik
    0.07
    éĿ©
    0.07
    à¸ŀร
    0.07
    705
    0.06
    ANDOM
    0.06
    Activations Density 0.003%

    No Known Activations