© 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. 18675
    Prev
    Next
    INDEX
    Explanations

    expressions related to customer service and relationship building

    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
    eldon
    -0.06
    -
    -0.06
     du
    -0.05
    bourne
    -0.05
     -
    -0.05
    ask
    -0.05
    borne
    -0.05
    the
    -0.05
     Bor
    -0.05
    ness
    -0.05
    POSITIVE LOGITS
    alion
    0.09
    avou
    0.09
    ÑĥлÑİ
    0.08
    ystack
    0.08
    SCRI
    0.07
    екаÑĢ
    0.07
    ÏĨÏīν
    0.07
    ocz
    0.07
    reon
    0.07
    agnost
    0.07
    Activations Density 0.002%

    No Known Activations