© 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. 87152
    Prev
    Next
    INDEX
    Explanations

    references to conflict and action in a narrative context

    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
    phylum
    -0.08
    åIJįçĦ¡ãģĹ
    -0.08
    ifetime
    -0.07
    fsp
    -0.07
    illance
    -0.07
    klady
    -0.07
    elden
    -0.07
    forman
    -0.07
    ãĥªãĤ«
    -0.07
    æĺŁæľŁ
    -0.07
    POSITIVE LOGITS
     fight
    0.07
     preparations
    0.06
     team
    0.06
     Team
    0.05
     led
    0.05
     plan
    0.05
     Plan
    0.05
    plan
    0.05
     preparation
    0.05
    udo
    0.05
    Activations Density 0.016%

    No Known Activations