© 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. 16794
    Prev
    Next
    INDEX
    Explanations

    inquiries or questions within the text

    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
    uptools
    -0.06
    imeter
    -0.06
    keh
    -0.06
    ansom
    -0.06
     Kral
    -0.06
    ewis
    -0.06
    kir
    -0.06
    .epam
    -0.06
     BT
    -0.05
    á»iji
    -0.05
    POSITIVE LOGITS
     why
    0.32
    why
    0.28
     Why
    0.28
     reasons
    0.27
    Why
    0.26
     WHY
    0.25
     reason
    0.25
     pourquoi
    0.21
     Reasons
    0.21
    çIJĨçĶ±
    0.20
    Activations Density 0.084%

    No Known Activations