© 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. 95612
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions of inclusion and emphasis

    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
    asal
    -0.08
    bole
    -0.07
    alama
    -0.07
    afen
    -0.07
    rate
    -0.07
    ilinear
    -0.07
    icot
    -0.07
    uitka
    -0.07
    forge
    -0.07
    dle
    -0.07
    POSITIVE LOGITS
    lig
    0.06
    ivre
    0.06
    ãĤĩãģĨ
    0.06
    λÏĮ
    0.06
    Injector
    0.06
     INST
    0.05
    redo
    0.05
    ntity
    0.05
     senses
    0.05
    chi
    0.05
    Activations Density 0.021%

    No Known Activations