© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 686
    Prev
    Next
    INDEX
    Explanations

    references to self-publishing and the comics industry

    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
     Shard
    -0.06
    段
    -0.06
    ór
    -0.06
     bottle
    -0.05
     carp
    -0.05
     Phar
    -0.05
     collar
    -0.05
    pty
    -0.05
     spar
    -0.05
     scientific
    -0.05
    POSITIVE LOGITS
     Comics
    0.08
     addslashes
    0.08
     comics
    0.07
     книж
    0.07
    rypted
    0.07
     Advance
    0.07
    меж
    0.07
    .inner
    0.07
     dcc
    0.07
    onne
    0.07
    Activations Density 0.148%

    No Known Activations