© 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. 61898
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "gram" and its variations in context

    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
    ym
    -0.08
    chu
    -0.07
    676
    -0.07
    eil
    -0.07
    980
    -0.07
     Chunk
    -0.07
    ymes
    -0.07
    reamble
    -0.07
    762
    -0.07
    ymm
    -0.07
    POSITIVE LOGITS
    atical
    0.09
    à¥Ģण
    0.09
    ophone
    0.09
    matic
    0.08
    atically
    0.07
     Cah
    0.07
    Pad
    0.07
    bling
    0.07
     Pad
    0.06
    bole
    0.06
    Activations Density 0.006%

    No Known Activations