© 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. 94901
    Prev
    Next
    INDEX
    Explanations

    themes related to tension and conflict in relationships or situations

    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
    å¥
    -0.07
    asticsearch
    -0.07
    728
    -0.06
     вел
    -0.06
    ulo
    -0.06
    åĭ
    -0.06
    esser
    -0.06
    _Enc
    -0.06
     اØ
    -0.06
    εÏģÏĮ
    -0.06
    POSITIVE LOGITS
     permanently
    0.10
     permanent
    0.08
     forever
    0.07
    æ°¸ä¹ħ
    0.07
     Forever
    0.06
    kov
    0.06
    ÏĦε
    0.06
    -caption
    0.06
     Plans
    0.06
    ampion
    0.06
    Activations Density 0.008%

    No Known Activations