© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 82695
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to numerical or statistical references

    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
    ntag
    -0.08
    enco
    -0.07
    _cmos
    -0.07
    zure
    -0.07
    طة
    -0.07
    ternet
    -0.07
    awy
    -0.07
    amaha
    -0.07
    itur
    -0.06
    eax
    -0.06
    POSITIVE LOGITS
    -sidebar
    0.07
    ãĤ«ãĥ¼
    0.07
    .inst
    0.07
    essler
    0.06
    \Entities
    0.06
    é½IJ
    0.06
     Ple
    0.06
    ÑģÑĮого
    0.06
    @[
    0.06
    ura
    0.06
    Activations Density 0.002%

    No Known Activations