© 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. 22-LLAMASCOPE-RES-131K
    11. 3899
    Prev
    Next
    INDEX
    Explanations

    terms that refer to significant quantities or sizes

    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
    chter
    -0.07
    xima
    -0.06
     situation
    -0.06
    _squared
    -0.06
    Enumerator
    -0.06
    ject
    -0.06
    edit
    -0.06
     situations
    -0.06
    ilen
    -0.06
     Height
    -0.06
    POSITIVE LOGITS
     number
    0.12
    -scale
    0.10
    number
    0.10
     número
    0.09
     numbers
    0.09
     sayıda
    0.08
     population
    0.08
     proportion
    0.08
    Domains
    0.08
    -number
    0.08
    Activations Density 0.039%

    No Known Activations