© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 60504
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and feedback appreciation

    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
    .semantic
    -0.07
    assi
    -0.07
    .foundation
    -0.06
    anges
    -0.06
    á»Ļp
    -0.06
     chá»īnh
    -0.06
    _HELPER
    -0.06
    uppe
    -0.06
    lication
    -0.06
    tha
    -0.06
    POSITIVE LOGITS
    odash
    0.09
    edback
    0.07
     (;;
    0.07
    bsd
    0.07
    ataka
    0.07
     Customer
    0.06
    feedback
    0.06
    egin
    0.06
     our
    0.06
    uml
    0.06
    Activations Density 0.002%

    No Known Activations