© 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. 74898
    Prev
    Next
    INDEX
    Explanations

    references to car brands and models

    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
    anta
    -0.06
    ÑĨик
    -0.06
     Elias
    -0.05
     Blick
    -0.05
    à¹ĩà¸Ļà¸Ń
    -0.05
    pio
    -0.05
    ÑĨо
    -0.05
    дап
    -0.05
    ialized
    -0.05
    rine
    -0.05
    POSITIVE LOGITS
    uforia
    0.08
     similarly
    0.08
     equivalents
    0.08
    endir
    0.07
     equivalent
    0.07
    lates
    0.07
    ones
    0.07
    ARB
    0.07
    itunes
    0.07
    Äł
    0.07
    Activations Density 0.055%

    No Known Activations