© 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. 29886
    Prev
    Next
    INDEX
    Explanations

    names of historical figures and politicians

    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
     Mann
    -0.06
    sein
    -0.06
    -history
    -0.06
    ANN
    -0.06
     history
    -0.06
    _manifest
    -0.06
    ResponseStatus
    -0.05
     Mai
    -0.05
    umbo
    -0.05
     MEMBER
    -0.05
    POSITIVE LOGITS
     era
    0.10
     Era
    0.10
     regime
    0.08
    ä»»
    0.08
     regimes
    0.07
     period
    0.07
    -period
    0.07
    -era
    0.07
     amet
    0.07
     ä»»
    0.06
    Activations Density 0.028%

    No Known Activations