© 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. 107971
    Prev
    Next
    INDEX
    Explanations

    references to measurement accuracy and reliability in scientific 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
     amen
    -0.07
    criptor
    -0.06
    üss
    -0.06
    erne
    -0.06
    ãģıãģł
    -0.06
    illac
    -0.06
    mrt
    -0.06
    avra
    -0.06
    mach
    -0.06
    kul
    -0.06
    POSITIVE LOGITS
     artifacts
    0.10
     bias
    0.09
     arte
    0.08
     artifact
    0.08
    Bias
    0.08
     Artifact
    0.07
    BarItem
    0.07
     sample
    0.07
     Bias
    0.07
    /sample
    0.07
    Activations Density 0.047%

    No Known Activations