© 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. 129405
    Prev
    Next
    INDEX
    Explanations

    phrases indicating legal distribution terms

    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
     crack
    -0.07
    Ñıг
    -0.07
    iterr
    -0.06
    AuthProvider
    -0.06
    REP
    -0.06
    yw
    -0.06
    alth
    -0.06
    ulsion
    -0.06
    برÛĮ
    -0.06
    gett
    -0.06
    POSITIVE LOGITS
     yesterday
    0.06
    Advisor
    0.06
     tomorrow
    0.06
    ierz
    0.06
    Pi
    0.06
     gram
    0.06
     Nes
    0.06
    apist
    0.06
     pi
    0.06
     spaces
    0.06
    Activations Density 0.000%

    No Known Activations