© 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. 40598
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to video game graphics and streaming quality

    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
    MPI
    -0.06
    oper
    -0.06
     deaf
    -0.06
    ssi
    -0.06
     oper
    -0.06
    erer
    -0.06
     latest
    -0.06
    ames
    -0.06
     verdi
    -0.06
     Fol
    -0.06
    POSITIVE LOGITS
    ois
    0.07
    íĴĪ
    0.07
    ollah
    0.07
    .datatables
    0.07
    afone
    0.07
    ivan
    0.07
    mai
    0.07
     ******************************************************************************↵
    0.07
    apus
    0.06
    Newsletter
    0.06
    Activations Density 0.007%

    No Known Activations