© 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. 5-LLAMASCOPE-RES-131K
    11. 125573
    Prev
    Next
    INDEX
    Explanations

    the preposition "to" used in various contexts

    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
    گر
    -0.08
    agli
    -0.08
     vur
    -0.08
    ritch
    -0.07
    isses
    -0.07
    semb
    -0.07
     evet
    -0.07
    iev
    -0.07
    ÑĭÑģ
    -0.07
    .scalablytyped
    -0.07
    POSITIVE LOGITS
     necessarily
    0.07
    icable
    0.07
    ew
    0.06
    rzy
    0.06
     substance
    0.06
    string
    0.06
     le
    0.06
    theless
    0.06
    mind
    0.06
     consumer
    0.06
    Activations Density 0.008%

    No Known Activations