© 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. 30631
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate an additional thought or idea

    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
    çĶļèĩ³
    -0.08
     even
    -0.07
     itself
    -0.07
    -FIRST
    -0.07
    'gc
    -0.06
    720
    -0.06
    even
    -0.06
    obao
    -0.06
    .jquery
    -0.06
     indeed
    -0.06
    POSITIVE LOGITS
    reds
    0.07
    resi
    0.07
    acci
    0.07
    Æ°á»
    0.07
    nown
    0.06
    kea
    0.06
    udio
    0.06
    spender
    0.06
     isNaN
    0.06
    CellValue
    0.06
    Activations Density 0.027%

    No Known Activations