© 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. 98716
    Prev
    Next
    INDEX
    Explanations

    terms related to equality and equal representation

    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
    INAL
    -0.07
    kills
    -0.07
    çĬ¶
    -0.06
    ese
    -0.06
    esian
    -0.06
    elastic
    -0.06
    nemonic
    -0.06
    anja
    -0.06
    onto
    -0.06
    efe
    -0.06
    POSITIVE LOGITS
    itarian
    0.09
    ateral
    0.08
    izer
    0.08
    ities
    0.08
    hart
    0.07
    .parseInt
    0.07
    hue
    0.07
    ityEngine
    0.07
    arily
    0.07
    igator
    0.07
    Activations Density 0.021%

    No Known Activations