© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 40045
    Prev
    Next
    INDEX
    Explanations

    references to positive relationships and connections among people

    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
     herself
    -0.18
    atrice
    -0.13
    woman
    -0.13
    彼女
    -0.12
     Woman
    -0.12
    å°ıå§IJ
    -0.12
     Actress
    -0.12
    daughter
    -0.12
    Woman
    -0.12
     Frau
    -0.12
    POSITIVE LOGITS
     guy
    0.14
     boys
    0.12
     men
    0.12
     boy
    0.12
     gentlemen
    0.12
     male
    0.12
     guys
    0.12
     himself
    0.12
     fathers
    0.12
     father
    0.12
    Activations Density 0.684%

    No Known Activations