© 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. 15-LLAMASCOPE-RES-131K
    6. 90391
    Prev
    Next
    INDEX
    Explanations

    technical details related to viruses and their biological processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Line break delimiters that separate entries in structured text content such as bibliographies, listings, and catalogs.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     ob
    -0.07
    arda
    -0.06
     in
    -0.06
     Pe
    -0.06
     for
    -0.06
     later
    -0.06
    astes
    -0.06
     ch
    -0.06
     pre
    -0.06
     In
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.09
    çε
    0.08
    (æ°´
    0.08
    LARI
    0.08
    'gc
    0.08
    çīĩ
    0.08
     hã
    0.08
    âĹİ
    0.08
    дап
    0.08
    ç¾
    0.08
    Activations Density 0.082%

    No Known Activations