© 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. 55593
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate relationship or influence, particularly involving the word "to"

    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
    ostel
    -0.09
    ection
    -0.08
    IFF
    -0.08
    ptal
    -0.08
    ï¸
    -0.08
    OGLE
    -0.08
    ehler
    -0.07
    CMS
    -0.07
     Beispiel
    -0.07
    رÙĬÙĦ
    -0.07
    POSITIVE LOGITS
     the
    0.13
     those
    0.10
    the
    0.10
     how
    0.08
     various
    0.08
    ÃĤ
    0.08
     what
    0.08
     a
    0.07
     certain
    0.07
     â
    0.07
    Activations Density 0.901%

    No Known Activations