© 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. 79994
    Prev
    Next
    INDEX
    Explanations

    occurrences of significant words in Portuguese related to acceptance or affirmative responses

    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
    abar
    -0.08
    tering
    -0.07
    tems
    -0.07
     Confidential
    -0.06
    mini
    -0.06
     Bars
    -0.06
    μοÏħ
    -0.06
    tered
    -0.06
    Bars
    -0.06
    ÛĮÚ©ÛĮ
    -0.06
    POSITIVE LOGITS
    .CreateIndex
    0.07
    ÐķС
    0.07
    ory
    0.07
    _permalink
    0.07
     modelBuilder
    0.06
     маÑĪи
    0.06
    opr
    0.06
     Hew
    0.06
     Rico
    0.06
     célib
    0.06
    Activations Density 0.000%

    No Known Activations