© 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. 17026
    Prev
    Next
    INDEX
    Explanations

    references to accountability and the consequences of actions

    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
    heel
    -0.08
    endra
    -0.08
    strup
    -0.07
    UBY
    -0.07
    ÙĥÙĬب
    -0.07
    makt
    -0.07
    á»ĵng
    -0.07
    TabPage
    -0.06
    ovan
    -0.06
    Soap
    -0.06
    POSITIVE LOGITS
     necess
    0.14
     necessity
    0.12
     forced
    0.10
     nécess
    0.10
    å¿ħé¡»
    0.10
     need
    0.10
     buá»Ļc
    0.10
     forcing
    0.09
     require
    0.09
    need
    0.09
    Activations Density 0.033%

    No Known Activations