© 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. 17-LLAMASCOPE-RES-131K
    11. 2072
    Prev
    Next
    INDEX
    Explanations

    themes related to self-identity and social disconnect

    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
    лек
    -0.08
    mart
    -0.07
    xima
    -0.07
     fierc
    -0.07
     transpose
    -0.06
    inho
    -0.06
    dess
    -0.06
    _TP
    -0.06
    ayout
    -0.06
    èģ
    -0.06
    POSITIVE LOGITS
     offline
    0.08
     Offline
    0.07
    oru
    0.06
    æĸ
    0.06
    飯
    0.06
    wf
    0.06
    chs
    0.06
     physical
    0.06
     social
    0.06
    aje
    0.06
    Activations Density 0.022%

    No Known Activations