© 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. 77528
    Prev
    Next
    INDEX
    Explanations

    instances of the word "so" used to express emphasis or connection

    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
    ariant
    -0.07
    sta
    -0.07
    td
    -0.06
    enga
    -0.06
    aga
    -0.06
    ming
    -0.06
    .dateTime
    -0.06
    ÑĥÑģа
    -0.06
    igua
    -0.06
    raphic
    -0.06
    POSITIVE LOGITS
     therefore
    0.09
    forth
    0.07
     forth
    0.07
    Therefore
    0.07
    ä¹İ
    0.07
    543
    0.07
    ONGLONG
    0.06
    SystemService
    0.06
     Therefore
    0.06
     predecess
    0.06
    Activations Density 0.008%

    No Known Activations