© 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. 9-LLAMASCOPE-RES-131K
    11. 96322
    Prev
    Next
    INDEX
    Explanations

    specific names and descriptors of notable individuals or entities

    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
    ORT
    -0.06
    ift
    -0.06
    orted
    -0.06
    atch
    -0.06
    Immutable
    -0.06
     Swords
    -0.06
     assorted
    -0.06
    igne
    -0.06
    rollable
    -0.06
     Cummings
    -0.06
    POSITIVE LOGITS
    /big
    0.08
    ngth
    0.07
    enga
    0.07
    ehr
    0.07
    uria
    0.07
    .ga
    0.07
    emoth
    0.07
    инов
    0.07
     Bust
    0.07
    aphrag
    0.06
    Activations Density 0.006%

    No Known Activations