© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 94033
    Prev
    Next
    INDEX
    Explanations

    actions and interactions in intimate or romantic contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ongs
    -0.07
    ParameterValue
    -0.07
    ucker
    -0.07
    æ°¸ä¹ħ
    -0.06
    çľī
    -0.06
     pilot
    -0.06
     network
    -0.06
    rray
    -0.06
     hostel
    -0.06
     permanent
    -0.06
    POSITIVE LOGITS
    åŁ
    0.07
     âĹĦ
    0.06
    borne
    0.06
    ismu
    0.06
     Garcia
    0.06
    oken
    0.06
    ÑĢива
    0.06
    porto
    0.06
    bourne
    0.06
    aniel
    0.06
    Activations Density 0.001%

    No Known Activations