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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 78118
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" across different 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
    otal
    -0.07
    quette
    -0.07
    поÑĢ
    -0.07
    ekim
    -0.06
    amaz
    -0.06
    اÙĨÙĪ
    -0.06
    dependence
    -0.06
    .escape
    -0.06
    abay
    -0.06
    irs
    -0.06
    POSITIVE LOGITS
     us
    0.09
     discretion
    0.07
    -us
    0.06
    ipt
    0.06
    ourt
    0.06
     individual
    0.06
     the
    0.06
     whether
    0.06
    丸
    0.06
     choice
    0.06
    Activations Density 0.010%

    No Known Activations