© 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. 15-LLAMASCOPE-RES-131K
    11. 61461
    Prev
    Next
    INDEX
    Explanations

    references and citations in documents

    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
    eda
    -0.06
    950
    -0.06
    unker
    -0.05
     excess
    -0.05
     scouts
    -0.05
    etric
    -0.05
    unny
    -0.05
    rg
    -0.05
    ware
    -0.05
    ò
    -0.05
    POSITIVE LOGITS
     hete
    0.10
     stub
    0.09
     hakk
    0.08
    áct
    0.08
     dikke
    0.08
    ebek
    0.08
     proport
    0.08
     prostitut
    0.08
    malink
    0.08
    ulo
    0.07
    Activations Density 0.021%

    No Known Activations