© 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. 92324
    Prev
    Next
    INDEX
    Explanations

    phrases containing variations of the word "plus"

    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
    castle
    -0.09
    eer
    -0.08
    .UnitTesting
    -0.08
    places
    -0.08
    PLACE
    -0.07
    /place
    -0.07
     plain
    -0.07
    flip
    -0.07
    zimmer
    -0.07
    Ø´ÙĪ
    -0.07
    POSITIVE LOGITS
    ieurs
    0.11
    -minus
    0.08
    vier
    0.08
    aire
    0.07
     ça
    0.07
    ahn
    0.07
    ene
    0.07
    quam
    0.07
    ature
    0.06
    ++++++++++++++++++++++++++++++++
    0.06
    Activations Density 0.009%

    No Known Activations