© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 88312
    Prev
    Next
    INDEX
    Explanations

    comparative and relational terms in various contexts

    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
    avis
    -0.07
    aph
    -0.07
    amble
    -0.06
    lege
    -0.06
    aret
    -0.06
    íĴĪ
    -0.06
     Dynamics
    -0.06
    uler
    -0.06
    ooke
    -0.06
    .mit
    -0.06
    POSITIVE LOGITS
    icans
    0.07
    .struts
    0.07
     repro
    0.06
    icontrol
    0.06
    æĹıèĩªæ²»
    0.06
    OKIE
    0.06
    ALLE
    0.06
     consum
    0.06
    ÙĬÙĦا
    0.06
     ÙħÙĤ
    0.06
    Activations Density 0.001%

    No Known Activations