© 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. 127758
    Prev
    Next
    INDEX
    Explanations

    the word "that" in various contexts

    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
    bish
    -0.07
    äm
    -0.06
    rish
    -0.06
     rằng
    -0.06
     unto
    -0.06
    ÑģÑĤиÑĤ
    -0.06
    jad
    -0.06
    vik
    -0.06
    er
    -0.06
    جÙĪ
    -0.06
    POSITIVE LOGITS
     Ùħباش
    0.07
    tica
    0.07
    mür
    0.06
    åīĩ
    0.06
    -Free
    0.06
    -Semit
    0.06
    -ÑĤо
    0.06
    roc
    0.06
    words
    0.06
    venir
    0.06
    Activations Density 0.005%

    No Known Activations