© 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. 15-LLAMASCOPE-RES-131K
    11. 103209
    Prev
    Next
    INDEX
    Explanations

    specific terms and variables related to mathematical concepts and data structures

    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
    reek
    -0.08
    ritch
    -0.07
    trand
    -0.07
    éłĵ
    -0.07
    eyh
    -0.07
    ãĥĪãĥ«
    -0.07
    achat
    -0.07
    .RemoveAll
    -0.07
    umo
    -0.07
    elez
    -0.07
    POSITIVE LOGITS
    474
    0.05
    ra
    0.05
     friendly
    0.05
    dur
    0.05
    rupt
    0.05
    legate
    0.05
     reconc
    0.05
     [~,
    0.05
     materially
    0.05
    FieldType
    0.05
    Activations Density 0.057%

    No Known Activations