© 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. 121071
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "in short," indicating summarization

    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
    ologue
    -0.07
    kok
    -0.06
    eger
    -0.06
    nd
    -0.06
    esinin
    -0.06
     Thick
    -0.06
     olursa
    -0.06
    ults
    -0.06
    rait
    -0.06
    inde
    -0.06
    POSITIVE LOGITS
    ë°Ķ
    0.07
     ########.
    0.06
    \Abstract
    0.06
    piler
    0.06
    braco
    0.06
    anyak
    0.06
     ActiveForm
    0.06
    ETCH
    0.06
    usion
    0.06
    üm
    0.06
    Activations Density 0.003%

    No Known Activations