© 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 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. 17-LLAMASCOPE-RES-131K
    11. 126627
    Prev
    Next
    INDEX
    Explanations

    important prepositions and conjunctions in the context of relationships and comparisons

    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
    \uc
    -0.08
    uguay
    -0.08
    .argument
    -0.07
    ConfigurationException
    -0.07
     annonces
    -0.07
    yms
    -0.06
    .inst
    -0.06
    duk
    -0.06
    iatric
    -0.06
    ocre
    -0.06
    POSITIVE LOGITS
    afari
    0.06
    ku
    0.06
    REDIENT
    0.06
    зÑĭ
    0.05
     friendly
    0.05
    atab
    0.05
    ÃŁ
    0.05
     itself
    0.05
    alc
    0.05
     Monetary
    0.05
    Activations Density 0.001%

    No Known Activations