© 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. 26647
    Prev
    Next
    INDEX
    Explanations

    specific numerical data or coded references in various formats

    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
    ations
    -0.10
    ing
    -0.09
    ates
    -0.09
    ions
    -0.09
    ians
    -0.08
    ists
    -0.08
    ING
    -0.08
    ings
    -0.08
    ers
    -0.08
    amente
    -0.07
    POSITIVE LOGITS
     Bulk
    0.07
    ymous
    0.07
    oyer
    0.07
    eve
    0.07
    eu
    0.07
    missive
    0.06
    .contentType
    0.06
    мом
    0.06
    ढ
    0.06
    parator
    0.06
    Activations Density 0.158%

    No Known Activations