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

    Neuronpedia

    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. 59562
    Prev
    Next
    INDEX
    Explanations

    technical or formal language related to programming or documentation

    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
    umu
    -0.07
    ove
    -0.06
    ahr
    -0.06
    oko
    -0.06
    angen
    -0.06
    ey
    -0.06
    SEA
    -0.06
    pher
    -0.06
    processable
    -0.06
    cca
    -0.06
    POSITIVE LOGITS
     tiener
    0.07
    ts
    0.07
    nts
    0.07
    ãĥ³ãĤ¸
    0.07
    ãĤ¯ãĥĪ
    0.06
     Dawn
    0.06
     Jennings
    0.06
    ÃľM
    0.06
    ãģ¥
    0.06
    ted
    0.06
    Activations Density 0.001%

    No Known Activations