© 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. 29123
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

    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
    .addObserver
    -0.09
    ây
    -0.09
    antity
    -0.09
    олож
    -0.08
    OutOfRangeException
    -0.08
     Orta
    -0.08
    égor
    -0.08
    .piece
    -0.08
    .writeln
    -0.08
    ække
    -0.08
    POSITIVE LOGITS
     throughout
    0.07
     Throughout
    0.06
     stead
    0.06
    ..
    0.06
    .
    0.06
     goddess
    0.06
    iod
    0.06
    5
    0.05
    ab
    0.05
    6
    0.05
    Activations Density 0.005%

    No Known Activations