© 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. 5-LLAMASCOPE-RES-131K
    11. 125745
    Prev
    Next
    INDEX
    Explanations

    references to nuclear weapons and missile development

    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
     lav
    -0.07
     Nan
    -0.07
    bis
    -0.06
    oba
    -0.06
    rup
    -0.06
    insk
    -0.06
    ç«ĭãģ¦
    -0.06
     Interval
    -0.06
    Ậ
    -0.06
    oir
    -0.06
    POSITIVE LOGITS
    chie
    0.07
     Singleton
    0.07
     Khu
    0.07
    engo
    0.07
    _SYN
    0.07
    arie
    0.06
    ahy
    0.06
    esin
    0.06
    olib
    0.06
    æĴŃ
    0.06
    Activations Density 0.004%

    No Known Activations