© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 61591
    Prev
    Next
    INDEX
    Explanations

    quotes from key figures or experts discussing issues related to health or economics

    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
     serialVersionUID
    -0.08
    utt
    -0.07
    سÙĪØ¨
    -0.07
     Byl
    -0.07
    ë°ľ
    -0.07
    Reporter
    -0.07
    lus
    -0.06
     wsz
    -0.06
    -spacing
    -0.06
    //:
    -0.06
    POSITIVE LOGITS
     analyst
    0.10
     experts
    0.10
     analysts
    0.10
     expert
    0.10
     anal
    0.09
     Experts
    0.09
     analysis
    0.08
     professor
    0.08
     Analyst
    0.08
    anal
    0.08
    Activations Density 0.050%

    No Known Activations