© 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. 120666
    Prev
    Next
    INDEX
    Explanations

    topics related to emotional and psychological struggles or conflicts

    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
    ียร
    -0.07
    ANCH
    -0.06
    oplevel
    -0.06
    ãĥ«ãĥķ
    -0.06
    roke
    -0.06
     spr
    -0.06
     Klo
    -0.06
     ÎķÏĢι
    -0.06
     Duffy
    -0.06
    اÙĦÙĦÙĩ
    -0.06
    POSITIVE LOGITS
    âĨIJ
    0.11
     âĨIJ
    0.08
    âŁ
    0.07
    Previous
    0.07
    lej
    0.07
     Jou
    0.06
    以åīį
    0.06
     минÑĥ
    0.06
    455
    0.06
    urret
    0.06
    Activations Density 0.009%

    No Known Activations