© 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. 71406
    Prev
    Next
    INDEX
    Explanations

    phrases related to software regulations and product eligibility

    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
     used
    -0.07
    å¥Ī
    -0.07
    ince
    -0.06
    Used
    -0.06
     Used
    -0.06
    Usage
    -0.06
     Fancy
    -0.06
     exhausted
    -0.06
    .VisualBasic
    -0.06
    bridge
    -0.06
    POSITIVE LOGITS
    ksen
    0.08
    aran
    0.08
    -gnu
    0.07
    åIJĪæł¼
    0.07
    etur
    0.07
     Guerrero
    0.07
     chứa
    0.07
    folio
    0.07
    BuilderInterface
    0.07
    azon
    0.07
    Activations Density 0.054%

    No Known Activations