© 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. 129540
    Prev
    Next
    INDEX
    Explanations

    colloquial language and informal phrases

    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
    ieber
    -0.06
     Helm
    -0.06
    ooth
    -0.06
    raci
    -0.06
    baugh
    -0.06
     lai
    -0.06
    å¡ļ
    -0.06
    ycastle
    -0.06
    alus
    -0.06
     svens
    -0.06
    POSITIVE LOGITS
     ok
    0.10
     okay
    0.10
     OK
    0.09
    ok
    0.08
    OK
    0.08
     understood
    0.07
    isci
    0.07
     understanding
    0.07
     Okay
    0.07
     promise
    0.07
    Activations Density 0.063%

    No Known Activations