© 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. 15-LLAMASCOPE-RES-131K
    11. 90551
    Prev
    Next
    INDEX
    Explanations

    references to ancestry and cultural heritage

    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
     ÎĶε
    -0.06
    output
    -0.06
    uid
    -0.06
    raises
    -0.05
     Raise
    -0.05
    å£
    -0.05
     Cause
    -0.05
    irical
    -0.05
    ets
    -0.05
    cause
    -0.05
    POSITIVE LOGITS
     ancient
    0.09
    ÐIJÑĢÑħÑĸв
    0.08
     historic
    0.08
    anc
    0.08
     anc
    0.07
    ohana
    0.07
     primitive
    0.07
    ','=',$
    0.07
    оби
    0.07
    auth
    0.07
    Activations Density 0.057%

    No Known Activations