© 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 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. 106553
    Prev
    Next
    INDEX
    Explanations

    instances of the word "related" and its variations indicating connections to other topics or information

    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
    istique
    -0.06
    ople
    -0.06
     Fé
    -0.06
    #Region
    -0.06
    onest
    -0.06
    atti
    -0.06
    Ñģов
    -0.06
     /*#__
    -0.06
    ίο
    -0.06
    594
    -0.06
    POSITIVE LOGITS
    ness
    0.09
    osh
    0.07
    ubo
    0.06
    142
    0.06
    oin
    0.06
     Ston
    0.06
    aint
    0.06
    ä»ĭ
    0.06
    ots
    0.06
    roids
    0.06
    Activations Density 0.004%

    No Known Activations