© 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. 4706
    Prev
    Next
    INDEX
    Explanations

    terms related to religious roles and commitments

    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
    baugh
    -0.07
    auga
    -0.07
    achinery
    -0.07
    ãĥ³ãĤº
    -0.07
    abaj
    -0.07
    portun
    -0.07
    achs
    -0.07
    odoxy
    -0.07
    arten
    -0.07
    á»įng
    -0.07
    POSITIVE LOGITS
    SEL
    0.08
    koli
    0.06
     Affero
    0.06
    åĸĦ
    0.06
    ac
    0.06
    ust
    0.06
    662
    0.06
    en
    0.05
    mun
    0.05
    elling
    0.05
    Activations Density 0.004%

    No Known Activations