© 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. 15-LLAMASCOPE-RES-131K
    11. 88913
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the passage of time or inevitability

    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
    еÑĢин
    -0.08
    AINS
    -0.07
    ecd
    -0.07
    ãģªãĤī
    -0.07
    orp
    -0.07
     trá»±c
    -0.07
    oret
    -0.06
    iaux
    -0.06
    contres
    -0.06
    afen
    -0.06
    POSITIVE LOGITS
    zk
    0.07
    irit
    0.07
     rival
    0.06
    ungan
    0.06
    aneously
    0.06
    iring
    0.06
     prest
    0.06
    712
    0.06
    ombo
    0.06
     whole
    0.06
    Activations Density 0.004%

    No Known Activations