© 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. 119953
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features of products

    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
    388
    -0.07
    StreamReader
    -0.06
     Ritch
    -0.06
    filt
    -0.06
     enthusiasts
    -0.06
    ë°
    -0.06
     Fitzgerald
    -0.06
    illet
    -0.05
    theme
    -0.05
    988
    -0.05
    POSITIVE LOGITS
    IDER
    0.07
    ibel
    0.07
    orna
    0.06
    voj
    0.06
    æĥ
    0.06
    ghan
    0.06
    ello
    0.06
    afx
    0.06
    adem
    0.06
    kke
    0.06
    Activations Density 0.006%

    No Known Activations