© 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 EvalsExportsAPI 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. 86138
    Prev
    Next
    INDEX
    Explanations

    references to product quality and parts in service descriptions

    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
    å·
    -0.06
    ãĤ¾
    -0.06
    yah
    -0.06
    RectTransform
    -0.06
    idy
    -0.06
     Majority
    -0.06
    諸
    -0.06
    ability
    -0.06
     Bless
    -0.05
    ãĥ³ãĤ¯
    -0.05
    POSITIVE LOGITS
    unger
    0.07
    uese
    0.07
    NullOr
    0.07
    عÙĦاÙħ
    0.07
     Cop
    0.07
    ibaba
    0.07
    ICA
    0.06
    -toolbar
    0.06
    Cash
    0.06
    iec
    0.06
    Activations Density 0.001%

    No Known Activations