© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 74901
    Prev
    Next
    INDEX
    Explanations

    references to the name "Lewis" in various 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
    tte
    -0.08
    ARAM
    -0.07
    unch
    -0.07
    eel
    -0.07
    IMER
    -0.07
    hesive
    -0.07
    .snp
    -0.07
    zilla
    -0.07
    eo
    -0.07
    UnitOfWork
    -0.07
    POSITIVE LOGITS
    ohn
    0.08
    son
    0.07
    iana
    0.07
    rence
    0.07
     ApplicationException
    0.07
     finally
    0.07
    lot
    0.07
    ville
    0.06
     acc
    0.06
    burg
    0.06
    Activations Density 0.004%

    No Known Activations