Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 106560
    Prev
    Next
    INDEX
    Explanations

    references to biological and germ warfare throughout history

    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
     Orr
    -0.07
    upe
    -0.06
     Adventure
    -0.06
    iske
    -0.06
     McCl
    -0.06
    Knife
    -0.06
    uzione
    -0.06
    avage
    -0.06
     average
    -0.06
     avent
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.09
    onta
    0.08
    /Area
    0.07
    èĺ
    0.07
     deployed
    0.07
    warf
    0.07
     WaitForSeconds
    0.07
    .xhtml
    0.07
     use
    0.06
    INI
    0.06
    Activations Density 0.023%

    No Known Activations