© 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. 78665
    Prev
    Next
    INDEX
    Explanations

    references to human rights violations and abuses

    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
     Dank
    -0.08
    .googlecode
    -0.07
    rous
    -0.07
    ç»
    -0.07
    Ư
    -0.06
    æĤª
    -0.06
    елÑİ
    -0.06
    yan
    -0.06
    agal
    -0.06
    stoff
    -0.06
    POSITIVE LOGITS
    secondary
    0.07
     arter
    0.06
    ignum
    0.06
    Secondary
    0.06
    /Internal
    0.06
    zp
    0.06
    opia
    0.06
     secondary
    0.06
     Secondary
    0.06
    .micro
    0.06
    Activations Density 0.021%

    No Known Activations