© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 95189
    Prev
    Next
    INDEX
    Explanations

    terms related to generational and intergenerational themes

    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
    æĿī
    -0.07
     slova
    -0.07
    лÑĥÑĩ
    -0.07
    azı
    -0.07
    esome
    -0.07
    ystate
    -0.07
    .sul
    -0.07
    див
    -0.07
    .logged
    -0.07
    uye
    -0.07
    POSITIVE LOGITS
     Perspectives
    0.06
    nal
    0.06
     perspectives
    0.06
    ime
    0.06
    396
    0.06
    -old
    0.06
    -olds
    0.05
    OLD
    0.05
     Cre
    0.05
     tested
    0.05
    Activations Density 0.004%

    No Known Activations