© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14906
    Prev
    Next
    INDEX
    Explanations

    terms related to email marketing and user engagement

    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
    arrow
    -0.06
    uned
    -0.06
    _TRACE
    -0.06
    ÏĦοÏį
    -0.06
     vrai
    -0.06
     dirt
    -0.06
    ÑĢаж
    -0.06
     boots
    -0.06
    Startup
    -0.06
    boot
    -0.06
    POSITIVE LOGITS
    egan
    0.07
    olina
    0.07
    oux
    0.07
    ä»ģ
    0.07
    odel
    0.07
    lava
    0.07
    agina
    0.06
    osaur
    0.06
    غÙĨ
    0.06
    Disappear
    0.06
    Activations Density 0.004%

    No Known Activations