© 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. 55023
    Prev
    Next
    INDEX
    Explanations

    statistical terms and computations related to data 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
    ildo
    -0.07
    amina
    -0.07
    Locker
    -0.07
    ando
    -0.06
    ipay
    -0.06
    slaught
    -0.06
    hta
    -0.06
    /apps
    -0.06
    hma
    -0.06
    embre
    -0.06
    POSITIVE LOGITS
     normal
    0.10
     mean
    0.10
     average
    0.10
     normals
    0.10
     historical
    0.09
     Normal
    0.09
     typical
    0.09
    normal
    0.08
     avg
    0.08
     norm
    0.08
    Activations Density 0.023%

    No Known Activations