© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 27624
    Prev
    Next
    INDEX
    Explanations

    phrases related to product replacement and return policies

    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
    	freopen
    -0.07
    modifiable
    -0.07
    anes
    -0.07
    θι
    -0.07
    rosso
    -0.06
    TestCategory
    -0.06
    .shell
    -0.06
    .scalablytyped
    -0.06
    .Selenium
    -0.06
    ÅĻit
    -0.06
    POSITIVE LOGITS
     replacements
    0.10
     replacement
    0.10
     Replacement
    0.08
     replace
    0.08
     replaces
    0.08
     replaced
    0.07
    replacement
    0.07
     Replace
    0.07
    Replacement
    0.07
    Locator
    0.07
    Activations Density 0.003%

    No Known Activations