© 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. 54426
    Prev
    Next
    INDEX
    Explanations

    phrases indicating existence or presence in varying contexts

    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
    omanip
    -0.09
    istra
    -0.08
    ESCO
    -0.07
    nbsp
    -0.07
    lsi
    -0.07
    \grid
    -0.07
    æ¸
    -0.07
    овеÑĢ
    -0.07
    .UnitTesting
    -0.07
    ãĥĥãĤ·ãĥ¥
    -0.07
    POSITIVE LOGITS
     definitely
    0.07
     respective
    0.07
    uno
    0.06
     certain
    0.06
     respectively
    0.06
     obviously
    0.06
     [
    0.06
    ayers
    0.06
    ¬
    0.06
     definite
    0.06
    Activations Density 0.027%

    No Known Activations