© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 88743
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate sources or authorship in descriptions

    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
    \_
    -0.07
    landa
    -0.07
    Ãły
    -0.07
    Ïģαν
    -0.07
    Unnamed
    -0.07
    imary
    -0.07
    озд
    -0.06
    Knife
    -0.06
    å¹³æĪIJ
    -0.06
     ($)
    -0.06
    POSITIVE LOGITS
     two
    0.07
    563
    0.07
     its
    0.07
     saying
    0.06
    izoph
    0.06
    395
    0.06
    ovÃŃ
    0.06
    opes
    0.06
     Fabric
    0.06
     Bott
    0.06
    Activations Density 0.056%

    No Known Activations