© 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. 76280
    Prev
    Next
    INDEX
    Explanations

    instances of conflict or discussions regarding permissibility in public representations or expressions

    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
     mek
    -0.07
    actionDate
    -0.07
    ãĤ¤ãĥī
    -0.07
    andom
    -0.07
    terdam
    -0.07
     дол
    -0.07
    è¾Ľ
    -0.07
    ιαν
    -0.06
    ÙĤات
    -0.06
    ãĥ¡ãĥ©
    -0.06
    POSITIVE LOGITS
    oyal
    0.07
    orang
    0.06
     deck
    0.06
     neutral
    0.06
    permit
    0.06
    íħIJ
    0.06
    letic
    0.06
     requests
    0.06
     request
    0.06
    ubble
    0.06
    Activations Density 0.010%

    No Known Activations