© 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 EvalsExportsAPI 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. 105817
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal values and self-assessment

    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
    inar
    -0.06
    å¼¥
    -0.06
     pari
    -0.06
    éĥİ
    -0.06
    cott
    -0.06
    ronics
    -0.06
    munition
    -0.06
    볬
    -0.06
    ahi
    -0.06
     Distrib
    -0.06
    POSITIVE LOGITS
     personal
    0.10
     own
    0.10
    èĩªå·±
    0.10
     personally
    0.09
    èĩªå·±çļĦ
    0.09
     Personal
    0.09
    Personal
    0.09
     Ñģебе
    0.09
     OWN
    0.08
     unique
    0.08
    Activations Density 0.053%

    No Known Activations