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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 82398
    Prev
    Next
    INDEX
    Explanations

    quantifiable changes in economic data

    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
     âĹĦ
    -0.08
    ativa
    -0.07
    unami
    -0.07
    íĺ¼
    -0.07
    wie
    -0.07
     fark
    -0.07
    à¤Ĥर
    -0.07
    .chapter
    -0.07
    atform
    -0.07
    erta
    -0.07
    POSITIVE LOGITS
    less
    0.07
    bery
    0.06
     particularly
    0.06
    iber
    0.06
     -
    0.06
    gap
    0.06
    bare
    0.06
    imer
    0.06
     amount
    0.06
    0.06
    Activations Density 0.020%

    No Known Activations