© 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. 60957
    Prev
    Next
    INDEX
    Explanations

    instances of lists or enumerations, particularly involving claims or assertions

    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
     alike
    -0.08
    éĤ£æł·
    -0.06
     váºŃy
    -0.06
     whose
    -0.06
    è¿Ļä¸Ģ
    -0.06
     that
    -0.06
    ues
    -0.06
    UFFIX
    -0.06
     this
    -0.06
    whose
    -0.06
    POSITIVE LOGITS
    ibri
    0.09
    inous
    0.08
    -ci
    0.08
    estre
    0.08
    langs
    0.08
    egal
    0.08
    _permalink
    0.08
    iner
    0.07
    egis
    0.07
    /animate
    0.07
    Activations Density 0.056%

    No Known Activations