© 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. 17-LLAMASCOPE-RES-131K
    11. 121398
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and social connections

    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
    enson
    -0.06
     regress
    -0.06
    gui
    -0.06
    anki
    -0.06
    pread
    -0.06
    izu
    -0.06
    ais
    -0.06
     len
    -0.06
     зали
    -0.06
     tit
    -0.06
    POSITIVE LOGITS
     strangers
    0.15
     stranger
    0.14
     unknown
    0.12
    unknown
    0.12
     acquaintance
    0.10
     Unknown
    0.10
     descon
    0.10
     UNKNOWN
    0.10
    _unknown
    0.10
    Unknown
    0.09
    Activations Density 0.035%

    No Known Activations