© 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. 98025
    Prev
    Next
    INDEX
    Explanations

    references to the frequency and consistency of posting content

    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
     arms
    -0.06
    stadt
    -0.06
     λÏĮγ
    -0.06
     labs
    -0.06
    vr
    -0.06
     Feedback
    -0.06
    apis
    -0.05
    k
    -0.05
     Lehr
    -0.05
    arms
    -0.05
    POSITIVE LOGITS
    -mf
    0.08
    .scalablytyped
    0.08
     Tan
    0.08
    éĹ»
    0.07
    ÏĩεδÏĮν
    0.07
    PLL
    0.07
    инок
    0.07
    elry
    0.07
    pone
    0.07
    olec
    0.07
    Activations Density 0.020%

    No Known Activations