© 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. 28497
    Prev
    Next
    INDEX
    Explanations

    references to parents and parenting-related concepts

    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
    rd
    -0.08
    bite
    -0.07
    ramework
    -0.07
    lÃŃÄį
    -0.07
    stants
    -0.07
    wner
    -0.07
    ibold
    -0.07
    	↵	↵	↵	↵
    -0.07
    sar
    -0.07
    curity
    -0.07
    POSITIVE LOGITS
    eral
    0.12
    thood
    0.10
    esco
    0.09
    ally
    0.09
    -child
    0.09
    ::__
    0.08
    age
    0.08
    erals
    0.08
    親
    0.08
    als
    0.07
    Activations Density 0.022%

    No Known Activations