© 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. 97990
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to divorce and marital dissolution

    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
     Tod
    -0.07
    rna
    -0.06
     Heck
    -0.06
     (?)
    -0.06
     intervention
    -0.06
    ulos
    -0.06
     Intervention
    -0.06
     Bolt
    -0.06
    iven
    -0.06
    isen
    -0.06
    POSITIVE LOGITS
    285
    0.07
    ockey
    0.07
    benchmark
    0.07
    andle
    0.07
    337
    0.07
    bens
    0.07
    Ïīδ
    0.07
    entiful
    0.07
    gua
    0.07
    erez
    0.07
    Activations Density 0.002%

    No Known Activations