© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 59163
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or names, particularly in a context related to celebrity or media

    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
    ickt
    -0.07
    Äįin
    -0.07
    anko
    -0.07
     Finished
    -0.06
    Ã
    -0.06
    llvm
    -0.06
     divid
    -0.06
    огод
    -0.06
    annon
    -0.06
     packageName
    -0.06
    POSITIVE LOGITS
     Roch
    0.07
    Caption
    0.07
     frontal
    0.07
    gel
    0.07
    olia
    0.07
     gr
    0.06
    bian
    0.06
     ramp
    0.06
    roperty
    0.06
     entr
    0.06
    Activations Density 0.003%

    No Known Activations