© 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. 118919
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their actions or criticisms

    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
    åł±
    -0.08
    /***/
    -0.07
     anonymous
    -0.07
    chner
    -0.07
    abal
    -0.06
    lle
    -0.06
     meille
    -0.06
     anonymously
    -0.06
    æĬ¥
    -0.06
    anonymous
    -0.06
    POSITIVE LOGITS
     often
    0.07
     stump
    0.07
     lately
    0.07
     during
    0.07
    often
    0.07
     Often
    0.06
     Vander
    0.06
     frequently
    0.06
    _recent
    0.06
     recently
    0.06
    Activations Density 0.014%

    No Known Activations