© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87023
    Prev
    Next
    INDEX
    Explanations

    assertions or declarations about something being a certain quality or state

    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
     Gentle
    -0.06
    esso
    -0.06
     Custom
    -0.06
     
    -0.06
    ens
    -0.06
    b
    -0.06
     threatening
    -0.06
     Magn
    -0.05
     há
    -0.05
    609
    -0.05
    POSITIVE LOGITS
    LEAN
    0.08
    imd
    0.08
    ÏģÎŃ
    0.08
    pta
    0.08
     ков
    0.08
    enties
    0.07
     огÑĢа
    0.07
    íĺĦ
    0.07
    spd
    0.07
    ozor
    0.07
    Activations Density 0.003%

    No Known Activations