© 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. 57827
    Prev
    Next
    INDEX
    Explanations

    references to live performances and community events

    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
    ELLOW
    -0.08
    eton
    -0.07
    brtc
    -0.07
    -fontawesome
    -0.07
    ntp
    -0.07
     пÑĢеÑģÑĤ
    -0.07
    owan
    -0.07
    озем
    -0.07
    msp
    -0.07
    Ìī
    -0.07
    POSITIVE LOGITS
    iyah
    0.06
     
    0.06
     cre
    0.06
    Helpers
    0.06
     Auxiliary
    0.06
    âĢĥ
    0.05
    ythe
    0.05
    nah
    0.05
    ÃŃk
    0.05
     area
    0.05
    Activations Density 0.013%

    No Known Activations