© 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. 9-LLAMASCOPE-RES-131K
    11. 95700
    Prev
    Next
    INDEX
    Explanations

    references to actors and film characters

    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
    ó
    -0.07
    anyl
    -0.06
    jem
    -0.06
    egal
    -0.06
    ób
    -0.06
    wer
    -0.06
    rale
    -0.06
    onde
    -0.06
    añ
    -0.06
    ane
    -0.05
    POSITIVE LOGITS
    ênh
    0.06
    yonel
    0.06
    769
    0.06
    filme
    0.06
    UnderTest
    0.06
    /Runtime
    0.06
     Bod
    0.06
     certs
    0.06
    .sap
    0.06
     jadx
    0.06
    Activations Density 0.010%

    No Known Activations