© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1556
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant experiences or events

    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
    ãĥ£
    -0.07
    ghi
    -0.06
    atism
    -0.06
    ekil
    -0.06
    į
    -0.06
    isha
    -0.06
    odia
    -0.06
    REA
    -0.06
    ICI
    -0.06
    éijij
    -0.06
    POSITIVE LOGITS
     initially
    0.10
     initial
    0.09
     earlier
    0.09
    Initially
    0.08
    -initial
    0.07
     Initially
    0.07
    initial
    0.07
     previous
    0.07
     inicial
    0.07
     пÑĢоÑĪ
    0.07
    Activations Density 0.041%

    No Known Activations