© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 4445
    Prev
    Next
    INDEX
    Explanations

    elements related to structured data and quantitative analysis

    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
     cur
    -0.07
    engo
    -0.07
    lenme
    -0.07
    çľĭ
    -0.07
     Zahl
    -0.07
    -toggler
    -0.06
     Cur
    -0.06
    uttgart
    -0.06
    ceptar
    -0.06
     prze
    -0.06
    POSITIVE LOGITS
     ranking
    0.08
     expert
    0.07
     Ranking
    0.07
     ranked
    0.07
     votes
    0.06
    olar
    0.06
     matrix
    0.06
     rankings
    0.06
     panel
    0.06
     experts
    0.06
    Activations Density 0.002%

    No Known Activations