© 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. 126868
    Prev
    Next
    INDEX
    Explanations

    instances of the word "by" 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
     behalf
    -0.07
     ma
    -0.06
    p
    -0.06
     bar
    -0.06
    pts
    -0.06
    اÙĦÙĥ
    -0.06
    hle
    -0.06
     Fres
    -0.06
    ably
    -0.05
    hurst
    -0.05
    POSITIVE LOGITS
     contrast
    0.08
     implication
    0.07
    ramid
    0.07
    otch
    0.07
    ynos
    0.07
    nila
    0.07
    contrast
    0.07
    achuset
    0.07
    etooth
    0.07
    //*[
    0.07
    Activations Density 0.024%

    No Known Activations