© 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. 57904
    Prev
    Next
    INDEX
    Explanations

    concepts related to spiritual growth and the process of transformation

    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
     recent
    -0.07
    /preferences
    -0.06
    ụ
    -0.06
     Verb
    -0.06
     lately
    -0.06
    ngo
    -0.06
     Latest
    -0.06
    æ»ħ
    -0.06
    ossil
    -0.06
    recent
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.10
     FontWeight
    0.07
    -self
    0.07
    Self
    0.07
    noinspection
    0.06
    Path
    0.06
    enic
    0.06
     ê°ľìĿ¸
    0.06
     oneself
    0.06
    arness
    0.06
    Activations Density 0.005%

    No Known Activations