© 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. 29689
    Prev
    Next
    INDEX
    Explanations

    entities related to governance and institutions

    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
    ussen
    -0.07
    ráž
    -0.07
    igraphy
    -0.07
    .ImageAlign
    -0.07
     Typed
    -0.07
    rouch
    -0.07
    rát
    -0.07
    ãĥ¼ãĥĨ
    -0.07
    illance
    -0.07
    orest
    -0.06
    POSITIVE LOGITS
     being
    0.10
    being
    0.07
     becoming
    0.07
     unable
    0.07
    çļĦæĥħ
    0.07
    rene
    0.07
     sendo
    0.07
    yster
    0.06
     go
    0.06
     Being
    0.06
    Activations Density 0.049%

    No Known Activations