© 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. 84450
    Prev
    Next
    INDEX
    Explanations

    references to multiple individuals or groups of people

    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
    imbus
    -0.07
    ä¸Ī夫
    -0.07
    ór
    -0.07
    eah
    -0.07
    hetto
    -0.07
    御
    -0.06
    itis
    -0.06
    ipes
    -0.06
     actionTypes
    -0.06
    byt
    -0.06
    POSITIVE LOGITS
    chwitz
    0.07
     crew
    0.07
     myself
    0.06
     others
    0.06
    Ñģок
    0.06
     Others
    0.06
    kest
    0.06
    .ToShort
    0.06
     münchen
    0.06
     frat
    0.06
    Activations Density 0.037%

    No Known Activations