© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 56991
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotional experiences and personal reflections

    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
    ritch
    -0.06
    åĿĤ
    -0.06
     ready
    -0.05
    quine
    -0.05
     bored
    -0.05
    xFFFF
    -0.05
     Lov
    -0.05
    nak
    -0.05
    ìĬµ
    -0.05
    olet
    -0.05
    POSITIVE LOGITS
    åıĹåĪ°
    0.09
     subject
    0.09
     bá»ĭ
    0.09
    fte
    0.08
    subject
    0.08
     SUBJECT
    0.07
    åıĹ
    0.07
     INTERRU
    0.07
    PEND
    0.07
    uffers
    0.07
    Activations Density 0.138%

    No Known Activations