© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 67
    Prev
    Next
    INDEX
    Explanations

    instances of emotional responses and their impacts

    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
     blame
    -0.07
     roli
    -0.07
    addtogroup
    -0.07
    मत
    -0.07
    kup
    -0.07
    iena
    -0.07
    strup
    -0.07
    asper
    -0.06
     пÑĥÑĤ
    -0.06
    OutOfBoundsException
    -0.06
    POSITIVE LOGITS
     reality
    0.06
    ãĥ¶
    0.06
    kir
    0.06
     tempered
    0.06
     concerns
    0.06
     realities
    0.06
     Fle
    0.06
    oji
    0.06
    pper
    0.05
    isos
    0.05
    Activations Density 0.028%

    No Known Activations