© 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. 41243
    Prev
    Next
    INDEX
    Explanations

    references to organizational resources and facilities

    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
     store
    -0.07
    berger
    -0.06
     Perc
    -0.06
     goggles
    -0.06
    _store
    -0.06
     onDataChange
    -0.06
    ุ
    -0.06
    enin
    -0.06
    friend
    -0.06
    athan
    -0.06
    POSITIVE LOGITS
     breakout
    0.10
     confer
    0.07
    %B
    0.07
     Conference
    0.07
     speaker
    0.07
     corporate
    0.07
     conference
    0.06
     Meeting
    0.06
     конÑĦ
    0.06
    격
    0.06
    Activations Density 0.004%

    No Known Activations