© 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. 88313
    Prev
    Next
    INDEX
    Explanations

    expressions of sympathy and support during times of loss

    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
    äºĮ人
    -0.08
    erb
    -0.07
    otec
    -0.07
     Loving
    -0.07
    lex
    -0.07
    ÑĢаÑģ
    -0.07
    minecraft
    -0.06
    _traits
    -0.06
    alis
    -0.06
    sak
    -0.06
    POSITIVE LOGITS
     those
    0.07
    ora
    0.06
     all
    0.06
     Chairs
    0.06
    aura
    0.06
     Mrs
    0.06
     Mr
    0.06
    auga
    0.06
     everyone
    0.06
     LRV
    0.06
    Activations Density 0.004%

    No Known Activations