© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 28495
    Prev
    Next
    INDEX
    Explanations

    mention of geographical features and their strategic importance

    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
    plen
    -0.06
     Underground
    -0.06
    mos
    -0.06
    -cons
    -0.06
    nen
    -0.05
     adult
    -0.05
     pestic
    -0.05
     Adult
    -0.05
    ttl
    -0.05
    iele
    -0.05
    POSITIVE LOGITS
     choke
    0.10
     Control
    0.09
    åħ¥åı£
    0.09
     entrance
    0.09
     Entrance
    0.09
     control
    0.09
     entrances
    0.09
    åĩºåı£
    0.09
     exits
    0.09
     blocking
    0.08
    Activations Density 0.049%

    No Known Activations