© 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. 27952
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their patterns within the text

    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
    ãģĻãĤĭãģ¨
    -0.08
    æĮĻ
    -0.08
    اÙĪÙĦ
    -0.07
    ковод
    -0.07
    uste
    -0.07
     strstr
    -0.06
     ADVISED
    -0.06
    Äĩe
    -0.06
     минÑĥ
    -0.06
    ehir
    -0.06
    POSITIVE LOGITS
     exception
    0.10
     exceptions
    0.10
     allerdings
    0.08
    (exception
    0.08
     occasional
    0.08
    Nevertheless
    0.08
     except
    0.08
     HOWEVER
    0.08
    iva
    0.07
     Nevertheless
    0.07
    Activations Density 0.071%

    No Known Activations