© 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. 75269
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ta."

    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
    RIX
    -0.07
    ãģ¸ãģ¨
    -0.07
    unan
    -0.07
     Nearby
    -0.06
     forb
    -0.06
    erna
    -0.06
    èĩº
    -0.06
    èĪ
    -0.06
     fakat
    -0.06
    .aspx
    -0.06
    POSITIVE LOGITS
    chia
    0.07
    anos
    0.07
    ollider
    0.07
     دار
    0.06
    itan
    0.06
    ÑĤÑĢо
    0.06
    four
    0.06
    enery
    0.06
    oksen
    0.06
    áÄį
    0.06
    Activations Density 0.000%

    No Known Activations