© 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. 97569
    Prev
    Next
    INDEX
    Explanations

    themes related to control and regulation

    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
    .scalablytyped
    -0.10
    ÑĤÑİ
    -0.08
    uslim
    -0.07
    antz
    -0.07
    hlas
    -0.07
    532
    -0.07
    Leaks
    -0.07
    paque
    -0.07
    .infinity
    -0.07
    PullParser
    -0.07
    POSITIVE LOGITS
    ÑĢави
    0.07
    CCI
    0.07
     unchecked
    0.07
    asonic
    0.06
     èį
    0.06
    chn
    0.06
    asil
    0.06
     Mercer
    0.06
    лон
    0.06
     Obt
    0.06
    Activations Density 0.018%

    No Known Activations