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. MLP Out
    5. 29-LLAMASCOPE-MLP-131K
    6. 5067
    Prev
    Next
    INDEX
    Explanations

    references to crime or criminal behavior

    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
     both
    -0.06
    eny
    -0.06
     stat
    -0.06
     null
    -0.06
    linkplain
    -0.06
    aux
    -0.06
     Ta
    -0.06
     Tier
    -0.06
     genuine
    -0.05
     Null
    -0.05
    POSITIVE LOGITS
    978
    0.08
    istrat
    0.08
    akis
    0.08
    .scalablytyped
    0.07
    893
    0.07
    167
    0.07
    166
    0.07
    314
    0.07
    979
    0.07
    289
    0.07
    Activations Density 0.048%

    No Known Activations