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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125986
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and systems, particularly in the context of data handling and health applications

    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
     wich
    -0.06
    à¹Ģà¸Ĺ
    -0.06
     Freund
    -0.06
    LES
    -0.05
    Prev
    -0.05
     Uncategorized
    -0.05
    .Dom
    -0.05
    809
    -0.05
    .Il
    -0.05
    â̦↵
    -0.05
    POSITIVE LOGITS
     via
    0.08
     without
    0.07
    efe
    0.07
     xong
    0.07
     VARIABLE
    0.07
    achen
    0.07
     Gaz
    0.07
     with
    0.07
    ufen
    0.07
    ãģĹãģ¦ãĤĤ
    0.07
    Activations Density 0.081%

    No Known Activations