© 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. 76822
    Prev
    Next
    INDEX
    Explanations

    references to book formatting and physical characteristics

    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
    oeff
    -0.08
    å¼
    -0.07
    LESS
    -0.07
    ogo
    -0.07
     patron
    -0.06
    ãĥ¬ãĤ¹
    -0.06
    ủa
    -0.06
    olie
    -0.06
    asso
    -0.06
    иÑģк
    -0.06
    POSITIVE LOGITS
    -sized
    0.10
    -size
    0.08
     sized
    0.07
    _accessible
    0.07
    ROM
    0.07
    ä¸Ī
    0.07
     size
    0.06
    ãĤµãĤ¤ãĤº
    0.06
     Tra
    0.06
    -length
    0.06
    Activations Density 0.002%

    No Known Activations