© 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. 15-LLAMASCOPE-RES-131K
    11. 61869
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters and political actions

    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
    395
    -0.07
    Emer
    -0.06
     Mini
    -0.06
    837
    -0.06
     mini
    -0.06
    asta
    -0.06
     dar
    -0.06
     actually
    -0.06
    841
    -0.06
     Rex
    -0.06
    POSITIVE LOGITS
     GPLv
    0.07
     himself
    0.07
    frauen
    0.07
    à¸ļาล
    0.07
    ãĤ¤ãĥĪ
    0.07
    åĭ
    0.07
    olin
    0.07
    iant
    0.07
    KeyType
    0.06
    @nate
    0.06
    Activations Density 0.021%

    No Known Activations