© 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. 119285
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their placement

    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
    ycin
    -0.07
    ĺIJ
    -0.07
    foil
    -0.06
    uchs
    -0.06
    igi
    -0.06
    ationToken
    -0.06
    Sir
    -0.06
    волÑı
    -0.06
     unb
    -0.06
     Comic
    -0.06
    POSITIVE LOGITS
     overall
    0.11
     Overall
    0.10
    Overall
    0.09
    overall
    0.09
     recommended
    0.08
     Rating
    0.08
    Rating
    0.07
     BOTTOM
    0.07
     Bottom
    0.07
    recommended
    0.07
    Activations Density 0.022%

    No Known Activations