© 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. 75984
    Prev
    Next
    INDEX
    Explanations

    multiple instances of facts, particularly when presented with qualifiers or emphasizing phrases

    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
    Others
    -0.07
    ari
    -0.06
    imax
    -0.06
    Compiled
    -0.06
    Hallo
    -0.06
     Others
    -0.06
    ucha
    -0.06
     Tato
    -0.06
    ê¸
    -0.06
    380
    -0.06
    POSITIVE LOGITS
     earlier
    0.07
     recently
    0.07
    å°±åľ¨
    0.07
     prior
    0.07
     former
    0.07
    æĽ¾
    0.07
    tring
    0.07
    owy
    0.07
    recent
    0.07
    ojis
    0.07
    Activations Density 0.042%

    No Known Activations