© 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. 129979
    Prev
    Next
    INDEX
    Explanations

    relationships and connections among names, symbols, and concepts

    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
    úp
    -0.07
    reh
    -0.07
    arie
    -0.07
    antz
    -0.06
    ialect
    -0.06
    udev
    -0.06
    ekil
    -0.06
    ARIABLE
    -0.06
     STAT
    -0.06
     contrasts
    -0.06
    POSITIVE LOGITS
     Dates
    0.07
    ç½²
    0.07
     datings
    0.06
     reconstructed
    0.06
    @qq
    0.06
    elden
    0.06
     Dash
    0.06
    åı¯èĥ½æĢ§
    0.06
    DBObject
    0.06
     zbyt
    0.06
    Activations Density 0.036%

    No Known Activations