© 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. 60455
    Prev
    Next
    INDEX
    Explanations

    references to user interactions or community engagement

    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
    holm
    -0.07
    Ñĥз
    -0.07
    _PROC
    -0.07
    itten
    -0.07
    ILED
    -0.06
    AGIC
    -0.06
     Vir
    -0.06
    ÑĢÑĥÑĩ
    -0.06
    raÄį
    -0.06
    Vir
    -0.06
    POSITIVE LOGITS
     logged
    0.10
     session
    0.09
     logout
    0.08
     login
    0.08
    session
    0.08
     guest
    0.08
    401
    0.07
     sess
    0.07
     Logout
    0.07
    -session
    0.07
    Activations Density 0.095%

    No Known Activations