© 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. 15-LLAMASCOPE-RES-131K
    11. 103229
    Prev
    Next
    INDEX
    Explanations

    complex emotional themes related to vulnerability and human connections

    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
    ammer
    -0.07
     zwar
    -0.07
    aga
    -0.06
    ytt
    -0.06
    esser
    -0.06
    enthal
    -0.06
    _exempt
    -0.06
    054
    -0.06
     Anast
    -0.05
    ستÙħ
    -0.05
    POSITIVE LOGITS
     equally
    0.14
     also
    0.12
    ä¹Łæľī
    0.11
    also
    0.10
    ä¹Łæĺ¯
    0.10
     ALSO
    0.10
     naopak
    0.09
     también
    0.09
     também
    0.09
     ÑĤоже
    0.09
    Activations Density 0.047%

    No Known Activations