© 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. 60971
    Prev
    Next
    INDEX
    Explanations

    structural classifications and divisions within categories

    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
    ej
    -0.07
     sonst
    -0.06
    ADER
    -0.06
    atorium
    -0.06
     such
    -0.06
    eo
    -0.05
     etc
    -0.05
    ician
    -0.05
    eer
    -0.05
    wort
    -0.05
    POSITIVE LOGITS
    bett
    0.07
    Either
    0.07
     Either
    0.07
     Firstly
    0.07
     ones
    0.07
    strup
    0.07
    either
    0.07
    ãģĿãĤĮãģ¯
    0.07
    ì°°
    0.06
     olanlar
    0.06
    Activations Density 0.032%

    No Known Activations