© 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. 54648
    Prev
    Next
    INDEX
    Explanations

    mentions of familial relationships and social connections

    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
    alles
    -0.08
    å¯Ħ
    -0.08
    ellas
    -0.08
    yun
    -0.07
    ogui
    -0.07
    deniz
    -0.07
    .numpy
    -0.07
    Ñĸж
    -0.07
    ENDER
    -0.07
    adar
    -0.07
    POSITIVE LOGITS
     family
    0.08
     spouse
    0.07
     relatives
    0.06
     friends
    0.06
     members
    0.06
     Jersey
    0.05
     glo
    0.05
     Loved
    0.05
     manufactured
    0.05
     Merry
    0.05
    Activations Density 0.016%

    No Known Activations