© 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. 86891
    Prev
    Next
    INDEX
    Explanations

    references to treasure hunting or exploration themes

    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
     AVL
    -0.09
    å»Ĭ
    -0.07
    raki
    -0.07
    rete
    -0.07
    acid
    -0.07
    ptune
    -0.06
    ãģ«ãģĬ
    -0.06
    _redirected
    -0.06
     tel
    -0.06
    semb
    -0.06
    POSITIVE LOGITS
     Ground
    0.07
     magnet
    0.07
     burial
    0.07
     Pros
    0.07
     mob
    0.07
     buried
    0.07
     magnetic
    0.07
     Field
    0.06
     ground
    0.06
     searcher
    0.06
    Activations Density 0.005%

    No Known Activations