© 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. 15-LLAMASCOPE-RES-131K
    11. 27105
    Prev
    Next
    INDEX
    Explanations

    elements of adventure and group dynamics in narratives

    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
     himself
    -0.11
    両
    -0.09
    his
    -0.09
     sám
    -0.08
     his
    -0.08
     его
    -0.07
     jeho
    -0.07
    åħ¼
    -0.07
     myself
    -0.07
    .onView
    -0.07
    POSITIVE LOGITS
     themselves
    0.17
     yourselves
    0.14
     nhau
    0.11
     their
    0.10
     collectively
    0.10
     Their
    0.10
    Their
    0.09
     together
    0.09
     collective
    0.09
    their
    0.09
    Activations Density 0.230%

    No Known Activations