© 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. 59023
    Prev
    Next
    INDEX
    Explanations

    gerunds and verbs related to completion or culmination

    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
    opoulos
    -0.07
    amon
    -0.07
    idges
    -0.07
     McInt
    -0.07
    kel
    -0.07
    ker
    -0.07
    ongan
    -0.07
    fried
    -0.07
    ither
    -0.06
    инки
    -0.06
    POSITIVE LOGITS
     with
    0.09
     Dit
    0.07
     cul
    0.07
     withd
    0.07
     when
    0.06
    582
    0.06
    with
    0.06
    YRO
    0.06
    cad
    0.06
    swith
    0.06
    Activations Density 0.012%

    No Known Activations