© 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. 17-LLAMASCOPE-RES-131K
    11. 118110
    Prev
    Next
    INDEX
    Explanations

    references to accountability and organizational structure

    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
    URLException
    -0.07
    eview
    -0.07
    âĢ¦↵↵
    -0.07
    AdapterManager
    -0.06
    SplitOptions
    -0.06
    ouz
    -0.06
    RecognitionException
    -0.06
    RuleContext
    -0.06
    ControlItem
    -0.06
    ByVersion
    -0.06
    POSITIVE LOGITS
    Question
    0.10
    Rpc
    0.07
    (IService
    0.07
    763
    0.06
    588
    0.06
     aforementioned
    0.06
    emble
    0.06
    791
    0.06
    &C
    0.06
    rientation
    0.06
    Activations Density 0.153%

    No Known Activations