© 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. 17-LLAMASCOPE-RES-131K
    11. 78374
    Prev
    Next
    INDEX
    Explanations

    terms associated with diagnostic testing and genetic analysis

    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
    izo
    -0.07
    dsn
    -0.06
    éĮ
    -0.06
    oids
    -0.06
    639
    -0.06
     action
    -0.06
    MRI
    -0.06
    829
    -0.06
    addtogroup
    -0.06
     Injector
    -0.06
    POSITIVE LOGITS
     analy
    0.08
     kits
    0.07
    Performed
    0.07
    Labor
    0.07
    ANEL
    0.07
    åijĬ
    0.07
     routine
    0.06
     blood
    0.06
    ollo
    0.06
    .lab
    0.06
    Activations Density 0.022%

    No Known Activations