© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 77663
    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
    #
    -0.08
    ekim
    -0.07
    alyze
    -0.07
    _Lean
    -0.07
    -alist
    -0.07
    heiro
    -0.07
    arella
    -0.07
     поба
    -0.07
    NECTION
    -0.07
    “But
    -0.07
    POSITIVE LOGITS
    hlen
    0.06
    icker
    0.06
     re
    0.06
    ÙĪع
    0.06
    oke
    0.06
    844
    0.05
    noch
    0.05
    -na
    0.05
     came
    0.05
    isRequired
    0.05
    Activations Density 0.019%

    No Known Activations