© 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. 93413
    Prev
    Next
    INDEX
    Explanations

    phrases related to retention or maintaining possession of items or concepts

    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
    ÌĨ
    -0.07
    oma
    -0.07
    ilt
    -0.06
    isma
    -0.06
    .scalablytyped
    -0.06
    ensure
    -0.06
    minent
    -0.06
     Maison
    -0.06
     ÙĦÙĢ
    -0.06
    /from
    -0.05
    POSITIVE LOGITS
    à¹Ħว
    0.09
     retain
    0.08
     unchanged
    0.08
    ãģ¾ãģ¾
    0.08
     retains
    0.08
    kus
    0.08
    ETCH
    0.07
    venes
    0.07
    etched
    0.07
    ãĥ³ãĥĪ
    0.07
    Activations Density 0.024%

    No Known Activations