© 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. 40586
    Prev
    Next
    INDEX
    Explanations

    instances of excessive or extreme quantities

    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
    .openg
    -0.08
    urry
    -0.08
    deniz
    -0.07
    onium
    -0.07
    ion
    -0.07
    ÑģÑİ
    -0.07
    echa
    -0.07
    onest
    -0.06
    MESS
    -0.06
    ernes
    -0.06
    POSITIVE LOGITS
     purposes
    0.12
     reasons
    0.11
    iaux
    0.08
    aging
    0.07
    bidden
    0.07
    IGIN
    0.07
    -profit
    0.07
    vik
    0.07
     instance
    0.06
     granted
    0.06
    Activations Density 0.058%

    No Known Activations