© 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. 126409
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their actions or proposals

    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
    itter
    -0.06
    aight
    -0.06
    ä¹±
    -0.06
     onDataChange
    -0.06
    太éĺ³åŁİ
    -0.06
    stra
    -0.06
     Dyn
    -0.05
     boyc
    -0.05
    _SS
    -0.05
     íŀĺ
    -0.05
    POSITIVE LOGITS
     annonces
    0.08
    Æ°á»Ŀng
    0.07
    ableObject
    0.07
    _packages
    0.07
     unpopular
    0.06
    SENS
    0.06
    ymoon
    0.06
    skill
    0.06
     Interior
    0.06
    оÑħ
    0.06
    Activations Density 0.031%

    No Known Activations