© 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. 15-LLAMASCOPE-RES-131K
    11. 61711
    Prev
    Next
    INDEX
    Explanations

    references to random number generation and matrix operations

    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
    ÙĪØ°
    -0.06
    åį
    -0.06
    uste
    -0.06
    -scripts
    -0.06
    oud
    -0.06
    lete
    -0.06
    umann
    -0.06
    ogn
    -0.06
    üven
    -0.06
    ëģĶ
    -0.06
    POSITIVE LOGITS
    apore
    0.07
    tplib
    0.06
     zel
    0.06
    ocab
    0.06
     horizon
    0.06
    toolbar
    0.06
    ÙĬز
    0.06
    Chip
    0.06
     Clamp
    0.06
     clue
    0.06
    Activations Density 0.013%

    No Known Activations