© 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. 71549
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "ever" and similar phrases indicating frequency or urgency

    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
    anka
    -0.06
    ogui
    -0.06
    angu
    -0.06
     mpl
    -0.06
     Caleb
    -0.06
    soc
    -0.06
    ERVER
    -0.06
    wap
    -0.06
    ibil
    -0.06
     altogether
    -0.06
    POSITIVE LOGITS
    476
    0.08
    theless
    0.07
    Ñħо
    0.07
    alls
    0.07
    blick
    0.07
    474
    0.07
    icher
    0.06
    ajas
    0.06
     Karlov
    0.06
    bows
    0.06
    Activations Density 0.002%

    No Known Activations