© 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. 1772
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions that suggest location or 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
    ika
    -0.07
    _viewer
    -0.06
    мена
    -0.06
    еÑī
    -0.06
    rouw
    -0.06
    arga
    -0.06
    à¸ĩาà¸Ļ
    -0.06
     Roberts
    -0.06
    prox
    -0.06
    _CS
    -0.06
    POSITIVE LOGITS
     beyond
    0.07
    ency
    0.06
    haar
    0.06
    istro
    0.06
    isted
    0.06
    ãĤ¯ãĥĪ
    0.06
    EMA
    0.05
    -through
    0.05
     Mild
    0.05
     wiki
    0.05
    Activations Density 0.028%

    No Known Activations