© 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. 29986
    Prev
    Next
    INDEX
    Explanations

    terms related to job transitions and replacements

    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
    ¸ı
    -0.08
     Pru
    -0.07
    isay
    -0.07
    _vendor
    -0.07
    Skeleton
    -0.07
    insula
    -0.07
    .shell
    -0.07
    _icons
    -0.06
    icons
    -0.06
    argas
    -0.06
    POSITIVE LOGITS
     replacement
    0.29
     replacements
    0.26
     successor
    0.26
     Replacement
    0.26
     replace
    0.26
     replaced
    0.24
     replacing
    0.23
    replacement
    0.23
    replace
    0.23
    Replacement
    0.22
    Activations Density 0.160%

    No Known Activations