© 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. 9-LLAMASCOPE-RES-131K
    11. 94466
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental and societal issues

    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
    onica
    -0.07
    avanaugh
    -0.06
    inia
    -0.06
    utsch
    -0.06
     thanks
    -0.06
    icide
    -0.06
    ìĵ°
    -0.06
    νÏī
    -0.06
    uš
    -0.06
    644
    -0.06
    POSITIVE LOGITS
    ankan
    0.07
    shan
    0.07
    usters
    0.07
    braco
    0.07
    ripple
    0.06
    lightbox
    0.06
    ksam
    0.06
     cue
    0.06
    OutOfBounds
    0.06
    auf
    0.06
    Activations Density 0.606%

    No Known Activations