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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-131K
    6. 11506
    Prev
    Next
    INDEX
    Explanations

    references to urban-related themes or terms

    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
    dong
    -0.06
    yro
    -0.06
    ousse
    -0.06
    opers
    -0.06
    gesi
    -0.06
    sb
    -0.06
     discrimin
    -0.06
    MainFrame
    -0.06
     DAM
    -0.06
     LICENSE
    -0.06
    POSITIVE LOGITS
    ears
    0.11
     Dictionary
    0.09
     Decay
    0.09
     Meyer
    0.08
     League
    0.08
    ophile
    0.08
    Dictionary
    0.08
     dictionary
    0.08
    icity
    0.08
    omic
    0.08
    Activations Density 0.005%

    No Known Activations