© 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. 16615
    Prev
    Next
    INDEX
    Explanations

    the name "Ey" and its variations in different 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
    ava
    -0.07
    bach
    -0.07
    oxy
    -0.07
    ãĥ³ãĤ°ãĥ«
    -0.06
    paged
    -0.06
    -ÑĤ
    -0.06
    acey
    -0.06
    artment
    -0.06
    lew
    -0.06
    ibu
    -0.06
    POSITIVE LOGITS
    thes
    0.09
    onus
    0.07
    lopedia
    0.07
    arak
    0.07
    odal
    0.07
    mour
    0.06
    duk
    0.06
    rede
    0.06
    vÃŃce
    0.06
    ture
    0.06
    Activations Density 0.006%

    No Known Activations