© 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. 71836
    Prev
    Next
    INDEX
    Explanations

    identifiers or codes, likely linked to specific subjects or categories

    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
    posables
    -0.07
    اÙī
    -0.07
    aphrag
    -0.07
    Ùĩر
    -0.07
    NEXT
    -0.07
    кÑĥÑĤ
    -0.07
    _VF
    -0.07
    adel
    -0.06
    emek
    -0.06
     Chanel
    -0.06
    POSITIVE LOGITS
    zag
    0.06
    itize
    0.06
    raquo
    0.06
    ite
    0.06
    _descr
    0.06
    åħµ
    0.05
     Amp
    0.05
    umer
    0.05
    _superuser
    0.05
    gn
    0.05
    Activations Density 0.040%

    No Known Activations