© 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. 94243
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "to."

    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
    etine
    -0.07
    park
    -0.07
    esti
    -0.06
    anou
    -0.06
     soon
    -0.06
    rox
    -0.06
     mortar
    -0.06
    Park
    -0.06
    bak
    -0.06
    omitempty
    -0.06
    POSITIVE LOGITS
    enis
    0.07
    uhn
    0.07
    ahl
    0.07
    ÙħاÙħ
    0.06
    ood
    0.06
    ãĤ¹ãĤ¯
    0.06
    _skin
    0.06
    олоÑĤ
    0.06
    asser
    0.06
    IColor
    0.06
    Activations Density 0.000%

    No Known Activations