© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 61174
    Prev
    Next
    INDEX
    Explanations

    terms related to definitions and formal statements in academic or scientific writing

    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
    vig
    -0.08
    edar
    -0.07
    asant
    -0.06
    ajan
    -0.06
    лÑı
    -0.06
    Montserrat
    -0.06
    inki
    -0.06
    ibi
    -0.06
    ospace
    -0.06
    pline
    -0.06
    POSITIVE LOGITS
     Borg
    0.07
     adel
    0.06
    .RunWith
    0.06
    izzard
    0.06
    hausen
    0.06
    aday
    0.06
     Saunders
    0.06
     Hawkins
    0.06
    807
    0.05
    CW
    0.05
    Activations Density 0.127%

    No Known Activations