© 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. 17-LLAMASCOPE-RES-131K
    11. 88151
    Prev
    Next
    INDEX
    Explanations

    intensifying adjectives that describe emotional or situational severity

    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
    hv
    -0.07
    mpi
    -0.07
     either
    -0.07
    anova
    -0.06
    onth
    -0.06
     far
    -0.06
    Inset
    -0.06
    PG
    -0.06
    npj
    -0.06
    داÙĨÙĦÙĪد
    -0.06
    POSITIVE LOGITS
    -than
    0.10
     because
    0.09
     when
    0.09
     fact
    0.08
    fact
    0.08
     than
    0.08
    icut
    0.07
     lorsque
    0.07
     THAN
    0.07
    because
    0.07
    Activations Density 0.013%

    No Known Activations