© 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. 29154
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to technology and its impact

    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
    âĸį
    -0.08
    çek
    -0.07
    pearance
    -0.07
    алÑİ
    -0.07
    (Spring
    -0.07
     IID
    -0.07
     tém
    -0.07
    ÙĪاع
    -0.07
     Ihren
    -0.07
    hti
    -0.07
    POSITIVE LOGITS
     envis
    0.07
     -
    0.07
     mr
    0.06
    osos
    0.06
     splitted
    0.06
     bevor
    0.06
     Wich
    0.06
    ocre
    0.06
    oso
    0.06
     âĢŀ
    0.06
    Activations Density 0.001%

    No Known Activations