© 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. 125183
    Prev
    Next
    INDEX
    Explanations

    concepts related to communication and understanding in context

    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
    utin
    -0.07
    legen
    -0.07
    agua
    -0.06
    ogl
    -0.06
    acerb
    -0.06
    _cleanup
    -0.06
    batim
    -0.06
    zk
    -0.06
    ixin
    -0.06
    ONY
    -0.06
    POSITIVE LOGITS
     understanding
    0.09
     understand
    0.09
     understands
    0.08
     Armed
    0.08
     design
    0.07
     decision
    0.07
     better
    0.07
     later
    0.07
     then
    0.07
     THEN
    0.07
    Activations Density 0.033%

    No Known Activations