© 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. 22-LLAMASCOPE-RES-131K
    11. 3703
    Prev
    Next
    INDEX
    Explanations

    specific time indicators and schedules

    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
    ient
    -0.08
    ousand
    -0.08
    ~-
    -0.08
    asher
    -0.07
    боÑĤ
    -0.07
    лÑĸд
    -0.07
    à¹ĩม
    -0.07
    ãĥ¼ãĥĬ
    -0.07
    oft
    -0.07
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.07
    POSITIVE LOGITS
    :
    0.11
    ï¸ı
    0.07
    :{}
    0.06
     contr
    0.06
    0.06
     beauty
    0.06
     nich
    0.06
     PM
    0.06
     Wagner
    0.06
    elage
    0.06
    Activations Density 0.010%

    No Known Activations