© 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. 4046
    Prev
    Next
    INDEX
    Explanations

    guidelines and principles related to ethical practices in journalism and content creation

    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
    otch
    -0.07
     bois
    -0.07
     Tune
    -0.07
    iddle
    -0.06
     misc
    -0.06
    åĨ¬
    -0.06
    .ld
    -0.06
    Dual
    -0.06
    ulus
    -0.06
     sab
    -0.06
    POSITIVE LOGITS
     synthesis
    0.10
     synthes
    0.08
     Syn
    0.08
     Transformation
    0.08
     transformation
    0.07
     synthesized
    0.07
     Transform
    0.07
     transformative
    0.07
     syn
    0.07
     SYN
    0.07
    Activations Density 0.062%

    No Known Activations