© 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. 77493
    Prev
    Next
    INDEX
    Explanations

    numerals and references to numerical data or statistical information

    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
     March
    -0.07
    zet
    -0.07
     October
    -0.07
     April
    -0.07
     February
    -0.06
     May
    -0.06
     July
    -0.06
     Blanc
    -0.06
    orz
    -0.06
     gamle
    -0.06
    POSITIVE LOGITS
    avigation
    0.08
    باØŃ
    0.08
    dbo
    0.07
    .exc
    0.07
    èĩ¨
    0.07
    رÙĪÛĮ
    0.07
    vertisement
    0.07
    /sdk
    0.07
    Wunused
    0.07
    woff
    0.07
    Activations Density 0.002%

    No Known Activations