© 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. 14540
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional experience and personal perspective

    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
    aliz
    -0.10
    nite
    -0.08
    angkan
    -0.08
    ỡ
    -0.08
    fak
    -0.08
    ÑĩеÑģ
    -0.07
    //{{
    -0.07
    aal
    -0.07
    aÄĩ
    -0.07
    celik
    -0.07
    POSITIVE LOGITS
     term
    0.06
     latter
    0.06
     plural
    0.06
     Wag
    0.06
     Flor
    0.06
     Ein
    0.06
    635
    0.06
     Esto
    0.05
     eup
    0.05
     di
    0.05
    Activations Density 0.052%

    No Known Activations