© 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 EvalsExportsinterp-engineNEWAPI 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. 62201
    Prev
    Next
    INDEX
    Explanations

    references to hierarchical positions or relationships

    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
     bergen
    -0.08
    eel
    -0.07
    ansi
    -0.07
    ,eg
    -0.07
    lain
    -0.07
     hend
    -0.07
     Painter
    -0.07
    foundation
    -0.07
     adel
    -0.06
     lÃłng
    -0.06
    POSITIVE LOGITS
     then
    0.16
    then
    0.12
     later
    0.12
     Then
    0.11
     second
    0.11
    	then
    0.10
    Then
    0.10
     THEN
    0.10
    _then
    0.09
     então
    0.09
    Activations Density 0.012%

    No Known Activations