© 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. 62544
    Prev
    Next
    INDEX
    Explanations

    numerical data relating to astronomical observations

    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
     pi
    -0.07
    ба
    -0.06
     label
    -0.06
    awan
    -0.06
     pem
    -0.06
    bron
    -0.06
    Cri
    -0.06
    BYTES
    -0.06
     cells
    -0.06
    Carthy
    -0.06
    POSITIVE LOGITS
     Maiden
    0.07
     Hass
    0.06
    íĨłíĨł
    0.06
    ile
    0.06
    GINE
    0.06
    iness
    0.06
     habit
    0.06
     Gree
    0.06
    ond
    0.06
    çĽijåIJ¬é¡µéĿ¢
    0.06
    Activations Density 0.001%

    No Known Activations