© 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. 105751
    Prev
    Next
    INDEX
    Explanations

    key elements and details about films and their adaptations

    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
    025
    -0.06
     terror
    -0.06
     Wagner
    -0.06
     security
    -0.06
    ÏĢλ
    -0.06
    ilon
    -0.06
     force
    -0.06
     Series
    -0.06
     Reform
    -0.06
    antity
    -0.06
    POSITIVE LOGITS
    HDR
    0.07
    ehler
    0.07
    TERS
    0.07
    Lifetime
    0.06
    รà¸ĩ
    0.06
     HDR
    0.06
    ifetime
    0.06
     ayar
    0.06
    اØŃ
    0.06
    ëħĦëıĦ
    0.06
    Activations Density 0.145%

    No Known Activations