© 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. 87284
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases related to health and genetic conditions

    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
    cord
    -0.06
    dü
    -0.06
    ейн
    -0.06
     Ones
    -0.06
    679
    -0.06
    atta
    -0.06
     Insecta
    -0.06
    åĿĢ
    -0.06
     вдÑĢÑĥг
    -0.05
    781
    -0.05
    POSITIVE LOGITS
    åı«
    0.11
    ä¸Ģç§į
    0.09
     called
    0.09
    jez
    0.09
     Pins
    0.07
     technique
    0.07
    ulan
    0.07
     particular
    0.07
     widely
    0.07
    called
    0.07
    Activations Density 0.032%

    No Known Activations