© 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. 78307
    Prev
    Next
    INDEX
    Explanations

    phrases related to business initiatives or promotional content

    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
    ãĥĸ
    -0.06
    bjerg
    -0.06
    htub
    -0.06
    iá»ģm
    -0.06
    .forName
    -0.06
     Wars
    -0.06
    ossa
    -0.06
     Leisure
    -0.06
    spiel
    -0.06
    .weixin
    -0.06
    POSITIVE LOGITS
     campaign
    0.07
    irez
    0.07
    abee
    0.07
    plemented
    0.06
    chner
    0.06
    OFF
    0.06
    ìĸ´ëĤĺ
    0.06
     Campaign
    0.06
    lbrace
    0.06
    erer
    0.06
    Activations Density 0.061%

    No Known Activations