© 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. 28185
    Prev
    Next
    INDEX
    Explanations

    instances of self-doubt and internal conflict

    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
    celik
    -0.06
    ãĥ«ãĤ¯
    -0.06
    ha
    -0.06
    baugh
    -0.06
     Gone
    -0.06
    eniable
    -0.06
    ÑĢÑıд
    -0.06
    ãĥ³ãĥĨ
    -0.05
    íħIJ
    -0.05
     tem
    -0.05
    POSITIVE LOGITS
     indeed
    0.15
     actually
    0.12
    inde
    0.12
     Indeed
    0.11
    Indeed
    0.10
     really
    0.09
    actually
    0.09
     altogether
    0.09
     Actually
    0.09
    -ÑĤаки
    0.08
    Activations Density 0.056%

    No Known Activations