© 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. 61138
    Prev
    Next
    INDEX
    Explanations

    references to secretive or exclusive social dynamics

    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
    ought
    -0.07
    ież
    -0.07
    OrFail
    -0.07
    imest
    -0.07
     wz
    -0.06
    ानद
    -0.06
    åŃĿ
    -0.06
     å¾
    -0.06
    eczy
    -0.06
    .Sdk
    -0.06
    POSITIVE LOGITS
    )=='
    0.06
    ij¸
    0.06
     Risk
    0.06
     Enlight
    0.06
    Å¡ÃŃ
    0.06
     unimagin
    0.05
    %%%
    0.05
    infos
    0.05
    undi
    0.05
    úp
    0.05
    Activations Density 0.002%

    No Known Activations