© 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. 71802
    Prev
    Next
    INDEX
    Explanations

    instances of contrast and qualifications in statements

    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
    dep
    -0.07
     not
    -0.07
    ntax
    -0.06
    sez
    -0.06
    anoi
    -0.06
     Mun
    -0.06
     Not
    -0.06
     Others
    -0.06
     NOT
    -0.06
     others
    -0.06
    POSITIVE LOGITS
     nor
    0.14
     certainly
    0.12
    Nor
    0.10
     neither
    0.10
    nor
    0.10
     tamp
    0.09
     sondern
    0.09
     Nor
    0.09
     Certainly
    0.09
     sÃŃ
    0.08
    Activations Density 0.029%

    No Known Activations