© 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 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. 82928
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an initial sequence or actions taken

    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
    okit
    -0.07
    emey
    -0.07
    apr
    -0.07
    ffen
    -0.07
    owie
    -0.07
    uguay
    -0.07
    uddenly
    -0.07
    rame
    -0.07
    uzey
    -0.07
    elah
    -0.07
    POSITIVE LOGITS
    åħĪ
    0.10
    elf
    0.07
    -before
    0.07
    Before
    0.07
    First
    0.07
    first
    0.07
    먼
    0.07
     åħĪ
    0.07
    ender
    0.06
    -first
    0.06
    Activations Density 0.008%

    No Known Activations