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

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 96264
    Prev
    Next
    INDEX
    Explanations

    phrases indicating prior achievements or completions

    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
    èĬ¬
    -0.07
    iol
    -0.07
    830
    -0.06
     theory
    -0.06
    kh
    -0.06
    /build
    -0.06
    igans
    -0.06
    630
    -0.05
    iffs
    -0.05
    znik
    -0.05
    POSITIVE LOGITS
    most
    0.07
    ·»
    0.07
    renderer
    0.07
    egal
    0.07
     been
    0.07
    CancelButton
    0.06
    wat
    0.06
     inform
    0.06
    ird
    0.06
    ört
    0.06
    Activations Density 0.009%

    No Known Activations