© 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. 118988
    Prev
    Next
    INDEX
    Explanations

    references to academic institutions or universities

    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
    uzzi
    -0.09
    pth
    -0.06
    bih
    -0.06
     cock
    -0.06
    iston
    -0.06
     Cock
    -0.06
     Rocky
    -0.06
    efeller
    -0.06
    Âł
    -0.06
    ichel
    -0.06
    POSITIVE LOGITS
     mastur
    0.08
     bbw
    0.07
    edin
    0.07
    岸
    0.07
    -ie
    0.07
     jadx
    0.06
    ovu
    0.06
     Ú©ÙĪØª
    0.06
    ìĨ
    0.06
    427
    0.06
    Activations Density 0.000%

    No Known Activations