© 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. 83596
    Prev
    Next
    INDEX
    Explanations

    expressions of inclusivity and support within organizations

    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
    752
    -0.06
     Obl
    -0.06
    792
    -0.06
     billig
    -0.06
     Programming
    -0.06
     sym
    -0.06
    ville
    -0.06
    TZ
    -0.06
    [][
    -0.06
     tonight
    -0.05
    POSITIVE LOGITS
    oq
    0.07
    HR
    0.07
     Hoover
    0.06
    ClientRect
    0.06
    ixer
    0.06
    à¤Ĺल
    0.06
    Äĥn
    0.06
    fen
    0.06
    :"-
    0.06
    onas
    0.06
    Activations Density 0.003%

    No Known Activations