© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 61100
    Prev
    Next
    INDEX
    Explanations

    interactions and relationships involving people and their experiences

    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
     Tiles
    -0.06
    ucc
    -0.06
    igin
    -0.06
     Gra
    -0.06
     also
    -0.06
    alla
    -0.05
    zenia
    -0.05
    qua
    -0.05
    ÅĤo
    -0.05
     anche
    -0.05
    POSITIVE LOGITS
     zwar
    0.08
    adol
    0.08
    æĹ¢
    0.08
     initially
    0.07
    наÑĩала
    0.07
    mtime
    0.07
    à¸Ļาà¸Ķ
    0.07
    ÏĦικ
    0.07
     vừa
    0.07
    _GB
    0.07
    Activations Density 0.173%

    No Known Activations