© 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. 75178
    Prev
    Next
    INDEX
    Explanations

    phrases that express emphasis or degree, particularly using the word "so" and its variants

    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
    rias
    -0.09
    campo
    -0.07
    ợ
    -0.07
     schön
    -0.07
    ıf
    -0.07
    rella
    -0.07
    sez
    -0.07
    ť
    -0.07
    quoi
    -0.07
    iali
    -0.07
    POSITIVE LOGITS
    ennie
    0.06
    aways
    0.06
    GetCurrent
    0.06
     still
    0.06
    asty
    0.06
    ãĥ©ãĥĥãĤ¯
    0.06
    encil
    0.06
     ÙģØ¥ÙĨ
    0.06
    arg
    0.06
    iard
    0.06
    Activations Density 0.003%

    No Known Activations