© 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. 75838
    Prev
    Next
    INDEX
    Explanations

    references to supernatural creatures and their societal structures

    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
    ective
    -0.07
    _ALIAS
    -0.07
    amaz
    -0.07
     Lag
    -0.07
    itive
    -0.06
     pam
    -0.06
    earable
    -0.06
    599
    -0.06
    é¼
    -0.06
    alias
    -0.06
    POSITIVE LOGITS
     attacking
    0.07
     attacks
    0.07
     victims
    0.07
     victim
    0.06
     attack
    0.06
     attacked
    0.06
     targets
    0.06
     Mate
    0.06
     inst
    0.06
    attack
    0.06
    Activations Density 0.018%

    No Known Activations