© 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. 56871
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives indicating extremes or the highest degree of a quality

    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
     enough
    -0.08
    allet
    -0.08
     Enough
    -0.07
    ish
    -0.07
    üçük
    -0.06
    isher
    -0.06
    ldr
    -0.06
    led
    -0.06
    kt
    -0.06
    eren
    -0.06
    POSITIVE LOGITS
    -ever
    0.14
    ablish
    0.12
    /sm
    0.10
    possible
    0.09
     possible
    0.09
    yet
    0.09
    /fast
    0.08
    -available
    0.08
    oft
    0.08
    most
    0.08
    Activations Density 0.051%

    No Known Activations