© 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. 9-LLAMASCOPE-RES-131K
    11. 95617
    Prev
    Next
    INDEX
    Explanations

    historical references to colonialism and territorial changes

    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
     str
    -0.06
    aille
    -0.06
    ley
    -0.06
     Ved
    -0.06
    ottage
    -0.06
    exampleInput
    -0.06
    byter
    -0.06
    ocha
    -0.05
     galleries
    -0.05
     bod
    -0.05
    POSITIVE LOGITS
     Hurt
    0.08
    IENT
    0.07
    961
    0.07
    .AUTO
    0.07
    ãģıãģł
    0.07
     nouvel
    0.06
     Slut
    0.06
    íķĺìĭł
    0.06
     Hub
    0.06
    ÏĥοÏħ
    0.06
    Activations Density 0.082%

    No Known Activations