© 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. 15-LLAMASCOPE-RES-131K
    11. 103982
    Prev
    Next
    INDEX
    Explanations

    references to business services and tour offerings

    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
    604
    -0.06
     Choices
    -0.05
     O
    -0.05
    lor
    -0.05
    -0.05
     Sur
    -0.05
     lor
    -0.05
    339
    -0.05
     Lor
    -0.05
    318
    -0.05
    POSITIVE LOGITS
    enberg
    0.10
    traits
    0.07
    usercontent
    0.07
     Ñģпад
    0.07
    chner
    0.07
    ague
    0.07
    agus
    0.07
    arius
    0.07
     numberOfRowsInSection
    0.07
    .intellij
    0.07
    Activations Density 0.002%

    No Known Activations