© 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. 40074
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions and events

    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
    itus
    -0.08
    ousel
    -0.08
    iminal
    -0.07
    kim
    -0.07
    rov
    -0.07
    isku
    -0.07
    etch
    -0.07
    IMPLEMENT
    -0.07
    wald
    -0.07
     norge
    -0.07
    POSITIVE LOGITS
    _INCLUDED
    0.08
     double
    0.06
    Weather
    0.06
    uble
    0.06
     weather
    0.06
    730
    0.06
     rev
    0.06
     analogy
    0.06
     pos
    0.06
    ysis
    0.06
    Activations Density 0.008%

    No Known Activations