© 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. 123982
    Prev
    Next
    INDEX
    Explanations

    causal and conditional phrases

    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
    ouz
    -0.06
    mailto
    -0.06
    lit
    -0.06
    ivre
    -0.06
    mens
    -0.05
     einem
    -0.05
    viol
    -0.05
    ictim
    -0.05
    ÃŃky
    -0.05
    令
    -0.05
    POSITIVE LOGITS
     they
    0.12
    they
    0.10
     it
    0.10
     theirs
    0.09
    ÙĪا
    0.09
    å®ĥ
    0.09
    They
    0.09
     há»į
    0.09
     nó
    0.08
     They
    0.08
    Activations Density 0.048%

    No Known Activations