© 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. 9-LLAMASCOPE-RES-131K
    11. 95706
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "did" in different contexts, indicating inquiry or expression of experience

    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
     now
    -0.07
    (ed
    -0.07
    adolu
    -0.07
    uai
    -0.07
    currently
    -0.06
    iez
    -0.06
     presently
    -0.06
    ehr
    -0.06
     currently
    -0.06
    vais
    -0.06
    POSITIVE LOGITS
     originally
    0.09
    ÅĽmy
    0.09
    actic
    0.08
    iator
    0.07
     yesterday
    0.07
    uppy
    0.07
     jsem
    0.07
    Lorem
    0.07
    ãĤĬ
    0.07
    лина
    0.07
    Activations Density 0.071%

    No Known Activations