© 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. 84588
    Prev
    Next
    INDEX
    Explanations

    programming and software-related terms and concepts

    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
    owie
    -0.07
    ê¶ģ
    -0.07
    alama
    -0.07
    zza
    -0.07
    .pipeline
    -0.07
    åĭ¤
    -0.07
    engin
    -0.07
    ëŁŃ
    -0.07
    ppe
    -0.07
    rek
    -0.07
    POSITIVE LOGITS
     health
    0.07
     Grace
    0.07
    Fabric
    0.06
    fabric
    0.06
    Grace
    0.06
    ypes
    0.06
    longleftrightarrow
    0.06
     consensus
    0.06
    idle
    0.06
    borg
    0.06
    Activations Density 0.023%

    No Known Activations