© 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. 56903
    Prev
    Next
    INDEX
    Explanations

    punctuation that indicates the conclusion of a thought or statement

    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
    301
    -0.06
     Schul
    -0.06
    los
    -0.06
     comed
    -0.06
     Keller
    -0.06
     susp
    -0.05
    anny
    -0.05
    lest
    -0.05
    arios
    -0.05
    unch
    -0.05
    POSITIVE LOGITS
    ebin
    0.07
    oleon
    0.07
    onestly
    0.07
    _lite
    0.07
    ietet
    0.07
    ijing
    0.07
    implify
    0.07
    yonel
    0.07
    evi
    0.06
    _audit
    0.06
    Activations Density 0.002%

    No Known Activations