© 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. 9-LLAMASCOPE-RES-131K
    11. 98490
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating relationships and connections between concepts or actions

    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
    yna
    -0.07
    ahkan
    -0.07
    hydr
    -0.07
    yro
    -0.07
    anas
    -0.07
    omor
    -0.07
    yr
    -0.07
    vais
    -0.07
    ehler
    -0.06
    icher
    -0.06
    POSITIVE LOGITS
     Ãĥ
    0.07
    'gc
    0.07
     â
    0.07
    //{{
    0.07
    ÙģاÙĦ
    0.07
    /*č↵
    0.07
     Sorted
    0.07
     âĢ
    0.07
    (DBG
    0.07
     “âĢ¦
    0.06
    Activations Density 0.637%

    No Known Activations