Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96224
    Prev
    Next
    INDEX
    Explanations

    references to myths and folklore

    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
    داد
    -0.07
    ossier
    -0.07
    eko
    -0.07
    essler
    -0.07
    yun
    -0.07
    est
    -0.07
    hart
    -0.07
    yclopedia
    -0.07
    isoft
    -0.06
    IENT
    -0.06
    POSITIVE LOGITS
    rious
    0.07
    fully
    0.07
    604
    0.07
    ological
    0.07
    osph
    0.06
     commissions
    0.06
     proven
    0.06
    otic
    0.06
    ousand
    0.06
    Ø©
    0.06
    Activations Density 0.011%

    No Known Activations