© 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. 56136
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their variations in context

    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
    arro
    -0.07
    ázev
    -0.07
    -même
    -0.07
    ichier
    -0.07
    elay
    -0.07
    olume
    -0.07
    å£°éŁ³
    -0.07
    ilenames
    -0.07
    iglia
    -0.06
    ÌĨ
    -0.06
    POSITIVE LOGITS
    jang
    0.06
    /-
    0.06
    /=
    0.06
    und
    0.06
     onCreateViewHolder
    0.06
    nda
    0.06
    ateg
    0.06
    decess
    0.06
     lÃł
    0.05
    çļĦæĺ¯
    0.05
    Activations Density 0.009%

    No Known Activations