© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 118958
    Prev
    Next
    INDEX
    Explanations

    words related to transitions or changes in state or condition

    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
     ÑĢеб
    -0.07
    immel
    -0.07
    ued
    -0.07
    çİī
    -0.06
     днÑı
    -0.06
    cht
    -0.06
    edla
    -0.06
    åŁİ
    -0.06
     menn
    -0.06
    ãĥ¼ãĥł
    -0.06
    POSITIVE LOGITS
    orage
    0.07
    leanup
    0.07
    ovy
    0.06
    arya
    0.06
    Reality
    0.06
    PCA
    0.06
    ablish
    0.06
     Chip
    0.06
    654
    0.06
    atty
    0.06
    Activations Density 0.027%

    No Known Activations