© 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. 119428
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "apply" and its variations in 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
    ắc
    -0.08
    нок
    -0.07
    holm
    -0.07
    synthesize
    -0.07
    EMPLARY
    -0.06
    avra
    -0.06
    usch
    -0.06
     ceremon
    -0.06
    aires
    -0.06
    adget
    -0.06
    POSITIVE LOGITS
     applied
    0.11
     apply
    0.10
     applies
    0.10
     applying
    0.10
    apply
    0.09
     Applied
    0.09
     Applying
    0.09
     Apply
    0.08
    .apply
    0.08
     brakes
    0.08
    Activations Density 0.015%

    No Known Activations